{ "data": { "a": { "slug": "arcmira", "name": "Arcmira", "vendor": "Arcmira, Inc.", "vendorUrl": "https://arcmira.com", "kind": "mcp", "category": "search", "summary": "Arcmira indexes YouTube and podcast transcripts and returns timestamped passages, entity mentions, channel sponsors and mention alerts through a remote MCP server, a REST API at api.arcmira.com/v1, a CLI and TypeScript and Python SDKs.", "url": "https://www.anchorterminal.com/tools/arcmira", "markdownUrl": "https://www.anchorterminal.com/tools/arcmira.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/arcmira.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/arcmira.json", "dns": "arcmira.grade.anchorterminal.com", "repo": "https://github.com/arcmira/mcp", "license": "Proprietary service under Arcmira's Terms of Service. The MCP server's source is public under an all-rights-reserved notice; the Claude Code plugin, the arcmira TypeScript SDK and CLI and the Python SDK are Apache-2.0, and the Famous rankings are CC BY 4.0", "transports": [ "streamable-http", "http" ], "remoteUrl": "https://mcp.arcmira.com/mcp", "packages": [ { "registry": "npm", "name": "arcmira" }, { "registry": "pypi", "name": "arcmira" } ], "auth": "mixed", "authNotes": "The MCP server at https://mcp.arcmira.com/mcp answers an unauthenticated request with 401 and an OAuth challenge naming its protected-resource document; hosts register themselves against api.arcmira.com, send the person to arcmira.com to sign in and consent, and get a token with the allowed scopes (read, monitors:write, trackers:write, recommendations:read) that refreshes on its own. Any client can instead send an account key as `Authorization: Bearer arc_sk_...`. Dashboard keys carry all four scopes and show once; a key minted from `POST /v1/signups` and `/v1/signups/verify` (an email and a six-digit code, no browser) carries `read` only and never expires. Keys are disabled on the API keys page and take effect at once; hosts are revoked under Dashboard, Integrations. Plan gates, not scopes, decide Premium transcripts, fresh media and sponsor rows.", "pricing": "freemium", "pricingNotes": "Free plan with 1,000 credits a month, 2 monitored names and no card, which withholds the newest 30 days of media and the pages past the first. Pro $20 a month for 20,000 credits (7-day trial, card required), Pro+ $60 for 60,000 with sponsor and recommendation rows, Ultra $200 for 400,000, Enterprise by contract; yearly billing 20 per cent less. A search passage, mention or list row costs 4 credits past the first 5 of a request, a momentum call 10, a sponsor row 40, a monitor alert 25, captions 4 per started 15 minutes and a Premium transcript 300 per started 15 minutes of the whole video, once. Past the plan, on-demand usage costs $0.002 a credit up to a budget an admin sets; repeating a request within 7 days and failed Premium transcripts cost nothing (https://arcmira.com/docs/usage-and-billing.md, checked 2026-10-30).", "priceSummary": "$0.001 / credit", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the OpenAPI file, llms.txt, developers.md, the docs or the pricing page (checked 2026-10-30). Paid plans and on-demand usage are billed to a card through Stripe from the dashboard.", "endpoints": [] }, "toolCount": 4, "popularity": { "githubStars": 78, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-30" }, "docsUrl": "https://arcmira.com/docs", "llmsTxt": "https://arcmira.com/llms.txt", "openapi": "https://api.arcmira.com/v1/openapi.json", "registryName": "io.github.arcmira/arcmira", "capabilities": [ "search.research", "audio.transcribe", "social.analytics" ], "tags": [ "hosted", "official", "closed-source", "openapi", "llms-txt", "mcp", "oauth", "cli", "typescript", "python", "webhooks", "free-tier", "no-card", "freemium", "pre-1.0", "agent-skills", "new" ], "lastRelease": "2026-10-15", "graded": true, "anchor": { "graded": true, "score": 64.2, "grade": "B", "agentReady": false, "rank": 483, "ranked": true, "rankOf": 1510, "categoryRank": 14, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 91, "maintenance": 84, "payments": 55, "reliability": 40, "schema": 87, "security": 61, "transparency": 61 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-02" }, "negative": -3, "negativeNotes": [ "Between 5 and 8 October 2026 the v1 API retired POST /v1/trackers (410 tracker_create_retired) and six tracker delivery fields for the team account model. The changelog says the first seven rows can break a client, and its entry is dated 8 October, the day the change finished, with no advance notice found. Documented the same day with typed codes, a 410 and a migration table, so deducted at the low end (-3). https://arcmira.com/docs/changelog.md" ], "verdict": "Four code-mode tools over a documented v1 API, OAuth with four scopes, a read-only sign-up key from two API calls and no card, and a 1,000-credit free month. No status page, SLA or security.txt, breaking v1 changes shipped in October with same-day notice, the server is at 0.10.7, and the index covers the shows Arcmira transcribes.", "bestFor": "Agents answering what was said on YouTube shows and podcasts, who was mentioned or appeared where, which brands sponsor a show and how a name's mentions are trending, with timestamped source links, through one connection on a free monthly allowance.", "strengths": [ "OAuth for MCP hosts with self-registration and four scopes, plus bearer keys that are read-only when minted from the API", "A public OpenAPI 3.1 file of 35 operations, an error catalogue of about 60 codes with `unlock.url` and `details.limit`, `Idempotency-Key` on every write and a request id on every response", "Four tools whose programs run in an isolate that never holds the key, bounded to 40 API calls, 30 seconds and 12,000 characters, with all four annotations declared", "Free plan of 1,000 credits a month without a card, prices in credits per read published on one page, and a key from two API calls with an email and a code", "Published limits of 60, 240 and 600 requests a minute by plan, `RateLimit-*` headers on every response and `Retry-After` on 429, and HMAC-SHA256 signed webhooks with secret rotation" ], "weaknesses": [ "No status page, incident history or SLA was found; the terms disclaim uninterrupted service and Enterprise lists priority support without an uptime commitment", "No security.txt on arcmira.com, no disclosure policy, bug bounty or certification, and the terms forbid probing for vulnerabilities", "The v1 API retired `POST /v1/trackers` and six tracker fields between 5 and 8 October 2026 with the changelog entry dated the day the change finished; the quickstart says routes arrive without notice", "The MCP server is at 0.10.7 after 33 registry versions in six weeks and two rounds of tool renames; the Free plan withholds the newest 30 days of media and pages past the first", "Every tool call, including the first 4,000 characters of the program and the agent's intent, is logged to the vendor's analytics with no opt-out, and the privacy policy states no retention periods", "Results are third-party speech with no prompt-injection guidance beyond checking the linked source, and support is one email address with no community channel" ], "agentNotes": [ "Call `arcmira_describe` once per session and write one program per question for `arcmira_execute_read`; return only the fields the answer needs, since output is cut at 12,000 characters and 3,000 per string.", "Resolve names with `arcmira.resolve` (free) before any `about`, `by`, `entity_ids` or `channel` filter; a name in a filter fails with `id_required`. Plain keyword search needs no resolver call.", "Check `arcmira.status()` or GET /v1/me for the plan, scopes and `usage.credits.available` before metered reads; on Free, media newer than 30 days and pages past the first fail with `freshness_requires_paid` and `pagination_gated`.", "A Premium read of an untranscribed video starts a transcription that uses credits (300 per started 15 minutes) and may return `pending`; read the same video again later, which is never charged twice, and send `retry: true` only when the user asks.", "Over HTTP send `Authorization: Bearer arc_sk_...`, an `Idempotency-Key` on every POST and PATCH, honour `Retry-After` on 429, and switch on `error.code`, following `unlock.url` on 402 and 403 rather than re-authenticating.", "Use `arcmira_execute_write` only after listing the user's monitors; it creates, follows and pauses but never deletes, and a connection made before server 0.9.0 answers `insufficient_scope` until reconnected." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.2 } ], "editorialScores": { "ergonomics": 91, "maintenance": 84, "payments": 55, "reliability": 40, "schema": 87, "security": 61, "transparency": 48 }, "provenanceScore": 73, "checked": { "categories": { "ergonomics": "2026-11-02", "maintenance": "2026-11-02", "payments": "2026-11-02", "reliability": "2026-11-02", "schema": "2026-11-02", "security": "2026-11-02", "transparency": "2026-11-02" }, "last": "2026-11-02", "lastMoved": "2026-10-30", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install arcmira", "http": "curl 'https://api.arcmira.com/v1/search?q=corporate%20cards\u0026limit=5' -H \"Authorization: Bearer $ARCMIRA_API_KEY\"", "claudeCode": "claude mcp add --transport http --scope user arcmira https://mcp.arcmira.com/mcp", "config": { "mcpServers": { "arcmira": { "url": "https://mcp.arcmira.com/mcp" } } } }, "letme": { "capability": "https://letme.dev/search.research", "tool": "https://letme.dev/arcmira" }, "area": "web-data", "unitPrices": [ { "item": "Search passage, mention or list row (Pro plan credit)", "unit": "credit", "usd": 0.001, "note": "a plan credit on Pro and Pro+; a passage, mention or list row costs 4 credits past the first 5 of a request, so a request of 5 or fewer rows costs nothing; $0.0005 a credit on Ultra" }, { "item": "On-demand credit", "unit": "credit", "usd": 0.002, "note": "usage past the plan's credits, up to an admin-set monthly budget, invoiced in steps from $20" }, { "item": "Premium transcript, 15 minutes", "unit": "call", "usd": 0.3, "note": "300 credits per started 15 minutes of the whole video, once per account, at $0.001 a Pro plan credit; $0.60 on-demand, $0.15 on Ultra" }, { "item": "Monitor alert", "unit": "call", "usd": 0.025, "note": "25 credits at $0.001 a Pro plan credit; $0.05 on-demand" }, { "item": "Sponsor or commercial row", "unit": "record", "usd": 0.04, "note": "40 credits, Pro+ and above only, at $0.001 a plan credit" }, { "item": "Pro plan", "unit": "month", "usd": 20, "note": "20,000 credits a month, 10 monitored names, 7-day trial with a card; Pro+ $60 for 60,000, Ultra $200 for 400,000; yearly billing 20 per cent less" } ], "provenance": { "legalEntity": "Arcmira, Inc.", "domain": "arcmira.com", "domainRegistered": "2014-06-05", "endpointOnVendorDomain": true, "terms": "https://arcmira.com/terms", "privacy": "https://arcmira.com/privacy", "statusPage": "", "changelog": "https://arcmira.com/docs/changelog", "securityTxt": "none", "checked": "2026-11-02", "notes": [ "The Terms of Service (effective 13 October 2026) and the privacy policy (effective 2 October 2026) name Arcmira, Inc., a company based in San Francisco, California, governed by California law with AAA consumer arbitration in San Francisco County. The contact address on both is contact@arcmira.com; support is hi@arcmira.com and sales is sales@arcmira.com.", "RDAP for arcmira.com gives a registration date of 2014-06-05 and a last change on 2024-09-10, the month the GitHub organisation was created (23 September 2024). The Wayback Machine holds captures of the domain from 2011 under earlier owners, so the registration date says nothing about the product's age.", "firstReleased is 2026-08-22, when the arcmira npm package was first published and the arcmira/arcmira repository's history begins. The vendor's docs changelog dates the first public API (v1.0.0) to April 2026 without a day, so the product is older than this date shows. The MCP server's first registry version, 0.3.0, is dated 4 September 2026.", "https://arcmira.com/.well-known/security.txt answered 404 on 2 November 2026 and /security.txt and /status answered 403; status.arcmira.com doesn't resolve. api.arcmira.com and mcp.arcmira.com weren't read on 2 November, and their 30 October security.txt answers are struck.", "robots.txt on arcmira.com disallows ClaudeBot, Claude-Web and anthropic-ai and allows Claude-User and Claude-SearchBot by name, with `Content-Signal: search=yes,ai-train=no,use=reference`; research continues on that basis, as the founder decided on 30 October 2026. On 2 November api.arcmira.com and mcp.arcmira.com serve only the Cloudflare-managed block (ClaudeBot disallowed, Claude-User not named), so they weren't read and the 30 October readings from them are struck. Paths disallowed for every agent (/api/, /dashboard, /search, /chat, /monitors and others) were not fetched." ], "score": 73 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/arcmira.json", "live": { "slug": "arcmira", "probe": { "target": "https://mcp.arcmira.com/mcp", "method": "mcp-initialize", "lastAt": "2026-11-07T19:21:53.048705731Z", "lastOk": true, "lastStatus": 401, "lastMs": 108, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 98, "p95ms24h": 314, "samples24h": 238, "samples30d": 1953, "days": [ { "date": "2026-10-30", "probes": 86, "ok": 86 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "versions": [ { "registry": "github", "name": "arcmira/mcp", "version": "v0.10.7", "released": "2026-10-15", "seenAt": "2026-11-06T23:07:04.092892737Z" }, { "registry": "mcp-registry", "name": "io.github.arcmira/arcmira", "version": "0.10.7", "seenAt": "2026-11-07T18:16:28.95801333Z" }, { "registry": "npm", "name": "arcmira", "version": "0.6.2", "seenAt": "2026-11-06T23:07:03.69880728Z" }, { "registry": "pypi", "name": "arcmira", "version": "0.6.2", "released": "2026-10-15", "seenAt": "2026-11-06T23:07:03.910131016Z" } ], "githubStars": 37, "npmWeekly": 2241, "pypiWeekly": 1960, "securityTxt": { "url": "https://arcmira.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:30.561117326Z" }, "llmsTxt": { "url": "https://arcmira.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:31:35.170990945Z" }, "domain": { "domain": "arcmira.com", "registered": "2014-06-05", "source": "https://rdap.verisign.com/com/v1/domain/arcmira.com", "checkedAt": "2026-11-01T14:10:03.976746256Z" }, "pages": [ { "url": "https://arcmira.com/docs/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T13:59:35.289640769Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "d9a4895b6976" }, { "url": "https://arcmira.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T13:59:37.690974671Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "8b2358d65d8d" }, { "url": "https://arcmira.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T13:59:39.728989013Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "68f7f882a190" } ], "mcpTools": { "url": "https://mcp.arcmira.com/mcp", "checkedAt": "2026-11-07T01:42:29.831100606Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-10-31T00:55:13.814941397Z" }, "github": { "repo": "arcmira/mcp", "checkedAt": "2026-11-02T08:20:57.108109932Z", "stars": 78, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-30T12:43:27Z", "openIssues": 5, "openPRs": 2, "issuesOpened90d": 7, "issuesClosed90d": 2, "prsMerged90d": 9, "ci": { "branch": "master", "runs": 9, "success": 9, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-10-30T12:43:54Z" }, "replies": { "sampled": 7, "unanswered": 5, "medianDays": 12.2 } }, "updatedAt": "2026-11-07T19:21:53.048705731Z" } }, "answer": "Perplexity Search API scores 70.2 (BB) on agent readiness against Arcmira's 64.2 (B), and leads in 3 of 7 scored categories. Arcmira leads on agent ergonomics, security \u0026 auth and payments \u0026 pricing.", "b": { "slug": "perplexity-search-api", "name": "Perplexity Search API", "vendor": "Perplexity", "vendorUrl": "https://www.perplexity.ai/", "kind": "http-api", "category": "search", "summary": "Perplexity's Search API returns ranked web results with extracted page text as JSON from Perplexity's own index, through `POST /search`. The same key reaches the Agent API's web_search tool for cited answers, and a hosted MCP server wraps both.", "url": "https://www.anchorterminal.com/tools/perplexity-search-api", "markdownUrl": "https://www.anchorterminal.com/tools/perplexity-search-api.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/perplexity-search-api.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/perplexity-search-api.json", "dns": "perplexity-search-api.grade.anchorterminal.com", "repo": "https://github.com/perplexityai/modelcontextprotocol", "license": "Proprietary service under the Perplexity API Terms of Service. The MCP server is MIT and the official SDKs Apache-2.0", "transports": [ "streamable-http", "stdio" ], "remoteUrl": "https://api.perplexity.ai/mcp", "packages": [ { "registry": "pypi", "name": "perplexityai" }, { "registry": "npm", "name": "@perplexity-ai/perplexity_ai" }, { "registry": "npm", "name": "@perplexity-ai/mcp-server" } ], "auth": "mixed", "authNotes": "Bearer Perplexity API key in the `Authorization` header. Keys belong to a project in the API console, are shown once, and can be generated and revoked through `/generate_auth_token` and `/revoke_auth_token`, with a rotation guide. No per-key scopes found. The hosted MCP server also accepts Sign in with Perplexity (OAuth), where the user picks the organisation to bill.", "pricing": "usage", "pricingNotes": "$5 per 1,000 successful Search API requests, or $1 with Fast Search, with up to five queries per request billed once. Invalid, rate-limited and failed requests are not billed. Agent API web_search is $2.50 per 1,000 calls plus model tokens. Prepaid credits with a card. No free allowance found.", "priceSummary": "$5 / 1k req", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Search API docs, the pricing page, the OpenAPI description or llms.txt (checked 2026-11-06). An empty balance returns 402 Payment Required with no payment requirements, per the FAQ.", "endpoints": [] }, "toolCount": 4, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.perplexity.ai/docs/search/overview", "llmsTxt": "https://docs.perplexity.ai/llms.txt", "openapi": "https://docs.perplexity.ai/openapi.json", "registryName": "ai.perplexity/mcp-server", "capabilities": [ "web.search", "search.answer", "search.research" ], "tags": [ "hosted", "usage-priced", "prepaid", "card-required", "closed-source", "openapi", "llms-txt", "mcp", "remote-mcp", "mcp-registry", "python", "typescript", "status-page", "soc2" ], "lastRelease": "2026-10-23", "graded": true, "anchor": { "graded": true, "score": 70.2, "grade": "BB", "agentReady": true, "rank": 211, "ranked": true, "rankOf": 1510, "categoryRank": 5, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 85, "maintenance": 82, "payments": 25, "reliability": 80, "schema": 89, "security": 56, "transparency": 66 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "Raw ranked results with token-capped page text from Perplexity's own index, $5 per 1,000 requests or $1 with Fast Search, an OpenAPI description and a hosted MCP server with read-only annotations. Uptime is not guaranteed, there is no free allowance, keys carry no scopes, and no guidance on untrusted page text was found.", "bestFor": "Agents on any model that need raw ranked sources with extracted text at a low per-request price, and teams that want cited answers from the same key through the Agent API.", "strengths": [ "OpenAPI 3.1 description of `POST /search` with enums and limits, llms.txt and a Markdown twin of every docs page", "`max_tokens`, `max_tokens_per_page` and `max_results` cap what reaches the model, and up to five queries share one billed request", "Per-request prices published without login, and invalid, rate-limited and failed requests are not billed", "Hosted MCP server with OAuth or a key; the local server is in the official registry under the verified ai.perplexity namespace", "security.txt valid to 31 December 2027, a SOC 2 Type II report and a SECURITY.md that takes private reports" ], "weaknesses": [ "The FAQ says uptime and recovery time are not guaranteed, and the terms carry no SLA", "No free allowance and prepaid credits with a card; Stripe Projects still needs a $10 purchase", "Project keys have no scopes or spending limits, so any key can run every API on the account", "No guidance on treating returned snippets as untrusted text was found in the docs or the MCP server", "The DPA says Perplexity Search may follow different data terms, and no retention period for search queries is stated" ], "agentNotes": [ "Set `max_tokens_per_page` and `max_tokens` before calling; extracted text otherwise fills the context, and the price does not change with size", "Skip results with an empty `snippet` and dedupe by `url` when sending a `query` array; each query costs one rate-limit unit", "Use `search_type: \"fast\"` for $1 per 1,000 when latency and cost matter more than depth", "On 429 wait for Retry-After, then back off; on 402 stop and ask the user to add credits", "Use the Search API for sources and the Agent API's web_search tool for a written answer with citations" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 70.2 } ], "editorialScores": { "ergonomics": 85, "maintenance": 82, "payments": 25, "reliability": 80, "schema": 89, "security": 56, "transparency": 51 }, "provenanceScore": 80, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install perplexityai", "http": "curl -X POST https://api.perplexity.ai/search \\\n -H \"Authorization: Bearer $PERPLEXITY_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"query\": \"renewable energy technologies\", \"max_results\": 10, \"max_tokens\": 50000, \"max_tokens_per_page\": 4096}'", "claudeCode": "claude mcp add --transport http perplexity https://api.perplexity.ai/mcp", "config": { "mcpServers": { "perplexity": { "url": "https://api.perplexity.ai/mcp" } } } }, "letme": { "capability": "https://letme.dev/web.search", "tool": "https://letme.dev/perplexity-search-api" }, "sameCompany": [ "perplexity-space", "pplx-decider", "pplx-decider-flash" ], "area": "web-data", "unitPrices": [ { "item": "Search API request", "unit": "1k-requests", "usd": 5, "note": "Up to five queries in one request billed once; failed and rate-limited requests not billed" }, { "item": "Search API request with Fast Search", "unit": "1k-requests", "usd": 1, "note": "`search_type: \"fast\"`" }, { "item": "Agent API web_search call", "unit": "1k-calls", "usd": 2.5, "note": "Plus model tokens; $1.00 with Fast Search" }, { "item": "Agent API fetch_url call", "unit": "1k-calls", "usd": 0.5, "note": "Plus model tokens" } ], "provenance": { "legalEntity": "Perplexity AI, Inc.", "domain": "perplexity.ai", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service", "privacy": "https://www.perplexity.ai/hub/legal/privacy-notice", "statusPage": "https://status.perplexity.com/", "changelog": "https://docs.perplexity.ai/docs/resources/changelog", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "The API Terms of Service (last updated 23 January 2026) name Perplexity AI, Inc. and California law. The Data Processing Addendum (last updated 13 August 2026) deletes personal data within 30 days of the service ending and notes that Perplexity Search may follow different data terms.", "www.perplexity.ai/.well-known/security.txt is valid until 31 December 2027 and links www.perplexity.ai/security.", "The status page moved to incident.io on 10 September 2026 and has Website, App, Computer and API components, with no separate Search component.", "docs.perplexity.ai/robots.txt allows the docs and carries Content-Signal ai-train=yes, search=yes, ai-input=yes. The terms have no clause on automated access to the website.", "The changelog dates entries by month only. Domain registration was not checked." ], "score": 80 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/perplexity-search-api.json", "live": { "slug": "perplexity-search-api", "probe": { "target": "https://api.perplexity.ai/mcp", "method": "get", "lastAt": "2026-11-07T19:22:25.812257306Z", "lastOk": true, "lastStatus": 401, "lastMs": 194, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 165, "p95ms24h": 266, "samples24h": 210, "samples30d": 210, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "vendorStatus": { "page": "https://status.perplexity.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T19:23:08.772447999Z" }, "versions": [ { "registry": "mcp-registry", "name": "ai.perplexity/mcp-server", "version": "1.2.1", "seenAt": "2026-11-07T18:16:28.95801333Z" }, { "registry": "npm", "name": "@perplexity-ai/mcp-server", "version": "1.3.0", "seenAt": "2026-11-06T23:55:31.394431614Z" }, { "registry": "npm", "name": "@perplexity-ai/perplexity_ai", "version": "0.41.0", "seenAt": "2026-11-06T23:55:30.575713692Z" }, { "registry": "pypi", "name": "perplexityai", "version": "0.46.1", "released": "2026-10-23", "seenAt": "2026-11-06T23:55:30.34668899Z" } ], "githubStars": 2612, "npmWeekly": 97298, "pypiWeekly": 401537, "securityTxt": { "url": "https://perplexity.ai/.well-known/security.txt", "state": "valid", "expires": "2027-12-31T00:00:00Z", "checkedAt": "2026-11-07T16:01:03.917430365Z" }, "llmsTxt": { "url": "https://docs.perplexity.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:33:36.681222085Z" }, "pages": [ { "url": "https://docs.perplexity.ai/docs/resources/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:07:27.675707255Z", "changedAt": "2026-11-06T13:29:48.535494355Z", "fingerprint": "a52a171e1f1f" }, { "url": "https://www.perplexity.ai/hub/legal/privacy-notice", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:32:54.875760985Z", "changedAt": "2026-11-06T13:53:25.792168971Z", "fingerprint": "29c9dd01613d" }, { "url": "https://www.perplexity.ai/hub/legal/perplexity-api-terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:32:50.897959644Z", "changedAt": "2026-11-06T13:53:22.592031411Z", "fingerprint": "6a7e4a95f45b" } ], "mcpTools": { "url": "https://api.perplexity.ai/mcp", "checkedAt": "2026-11-07T01:46:49.011542458Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:46:49.011542458Z" }, "updatedAt": "2026-11-07T19:23:08.772447999Z" } }, "edges": [ { "by": 40, "category": "reliability", "leads": "perplexity-search-api", "name": "Reliability", "reasons": { "a": "Hosted reading, for the MCP server with the HTTP API it fronts. No public status page was found on 2 November. None is linked from the docs, llms.txt, developers.md or the footer, https://arcmira.com/status answers 403 and status.arcmira.com does not resolve (0). No readable incident history, so the floor (5). Limits are published with numbers on the Plans and usage page, 60 requests a minute per key on Free, 240 on paid plans and 600 on Enterprise, with RateLimit-Limit, RateLimit-Remaining and RateLimit-Reset on every authenticated response and a 30-a-minute cap on bad keys per address (15). 429 rate_limited carries Retry-After and retry_after_seconds, developers.md asks for exponential backoff, 503 search_unavailable and transcript_fetching carry Retry-After, every POST and PATCH takes an Idempotency-Key that replays with Idempotency-Replayed, a repeated Premium read is never charged twice, and a webhook secret can be recovered under its key for 24 hours (15). No SLA. The terms (effective 13 October 2026) disclaim uninterrupted or error-free service, and the Enterprise page lists priority support but no uptime commitment (0). The HTTP API is /v1 at document version 1.0.0 with nothing labelled beta, but the MCP server agents connect to is 0.10.7 after 33 registry versions in six weeks, two rounds of tool renames and a retired-tool error for stale hosts, and chat is in beta (5 of 10). 0+5+15+15+0+5 = 40.", "b": "Graded on the hosted lines, for `POST /search` and the hosted MCP server. status.perplexity.com, on incident.io since 10 September 2026, has an API component with an RSS feed and a JSON summary. There is no separate Search component (20). In the 90 days from 8 August the feed lists 'Investigating API issue' on 13 August, resolved with no detail, a usage-based billing issue on 3 September, and on 9 October elevated errors on the website, app and Computer, where the API 'remained operational throughout'. Minor only, with the caveat that history before the migration may be incomplete (20). The Search API is limited to 50 query units a second with a burst of 50 on every tier, and the other APIs publish QPS and token limits per tier (15). 429 carries Retry-After and an `error.type`, the SDKs retry 429 and 5xx twice honouring Retry-After, the Search best-practices page shows backoff, and failed or rate-limited searches are not billed. Searches have no side effects (15). The FAQ says Perplexity does not guarantee uptime, failure frequency or recovery time, and the terms carry no SLA (0). No beta label on the Search API, launched on 25 September 2025 (10). 20 + 20 + 15 + 15 + 0 + 10 = 80." }, "scores": { "a": 40, "b": 80 } }, { "by": 30, "category": "payments", "leads": "arcmira", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 in the OpenAPI file, llms.txt, developers.md, the docs or the pricing page (0). Prices published without a login, in credits per read (4 a passage, mention or list row past the first 5 of a request, 10 a momentum call, 40 a sponsor row, 25 an alert, 4 per started 15 minutes of captions, 300 per started 15 minutes of a Premium transcript) and in dollars (Pro $20 for 20,000 credits, Pro+ $60 for 60,000, Ultra $200 for 400,000, on-demand $0.002 a credit) (20). Free plan with 1,000 credits a month, 2 monitored names and no card, per the pricing FAQ; the 7-day Pro trial needs a card (20). POST /v1/signups with an email and POST /v1/signups/verify with the six-digit code return a read-scoped key with no browser, so an agent with a mailbox can onboard itself; the code still has to be read from an inbox, and write scopes need a dashboard key or OAuth consent (15 of 20). 0+20+20+15 = 55.", "b": "No x402, MPP or L402 in the docs, pricing page, OpenAPI or llms.txt (0). $5 per 1,000 successful requests, $1 with Fast Search, published without a login, with failed and rate-limited requests not billed (20). Usage is prepaid with a card on the billing page, and no free allowance was found. The console playground needs no key but is a page for a person, not an API allowance (0). A person signs up in the console. The Stripe Projects route provisions a project, key and credits from a terminal, but needs a person's Stripe account with a payment method and a $10 minimum purchase (5 of 20, as on the Decisions API listing). 0 + 20 + 0 + 5 = 25." }, "scores": { "a": 55, "b": 25 } }, { "by": 6, "category": "ergonomics", "leads": "arcmira", "name": "Agent ergonomics", "reasons": { "a": "MCP reading. Four tools whose definitions are short, but arcmira_describe returns a reference the vendor measures at 23,124 characters, loaded once a session, and the server instructions run to 1,995 characters; the vendor's own measurement for the change to code mode was 1,123 tokens of definitions against 8,163 for the earlier ten tools (18 of 25). limit 1 to 20 on search (default 5), cursors and has_more on lists, after and before windows, about, by, kind, channel and entity filters, start and end on transcripts, and program output capped at 12,000 characters, 3,000 per string and 100 per array, so a program returns only the fields an answer needs (20). One error envelope with a stable code, a message, param, gate, unlock.url, details.limit, retry_after_seconds and request_id, surfaced to the model with isError and the call_id to report (20). Idempotency-Key on every POST and PATCH with a replay header, a Premium read that is never charged twice, writes that pause rather than delete, and all four annotations declared on every tool; arcmira_execute_read is marked not read-only because a Premium read can start a transcription that uses credits, which a strict host may treat as a write (18 of 20). Few required inputs (one search string, ids resolved for free), a 90-day default window, defaults on limit, and official Apache-2.0 SDKs for TypeScript (npm arcmira 0.6.2) and Python (pip arcmira, repository v0.6.2) plus a CLI, with the caveat that the MCP client's argument names differ from the HTTP and SDK names (15). 18+20+20+18+15 = 91.", "b": "`max_results` 1 to 20, `max_tokens` and `max_tokens_per_page` cap the extracted text, and results are title, url, snippet and two dates. The MCP server has four tools (23 of 25). Domain, language, recency, publication and update date filters and `country`, with up to five queries in one request. No pagination or offset (16 of 20). 429 bodies name the limit hit, the SDKs map status codes to typed errors, and 402 marks an empty balance. Search-specific error bodies beyond 422 validation are not documented (13 of 20). Searches only read, failed and rate-limited requests are not billed, and the MCP server sets readOnlyHint true, destructiveHint false and idempotentHint false on every tool (18 of 20). Only `query` is required. Official Python and TypeScript SDKs, a CLI and a Python Search SDK (15). 23 + 16 + 13 + 18 + 15 = 85." }, "scores": { "a": 91, "b": 85 } }, { "by": 5, "category": "security", "leads": "arcmira", "name": "Security \u0026 auth", "reasons": { "a": "OAuth for MCP hosts (the server's source answers a bare request with a 401 naming its protected-resource document, which lists the scopes read, monitors:write, trackers:write and recommendations:read; the README says the host registers itself against api.arcmira.com and its tokens refresh; the docs give sign-in tokens an hour that refresh for 30 days, revoked per host in the dashboard; PKCE and the introspection and revocation endpoints were read on 30 October from api.arcmira.com's metadata, a host this run no longer reads, so they are struck) and arc_sk_ keys sent only as a bearer header, shown once, several per account with a label and last-used time, disabled at once; sign-up keys carry read only and dashboard keys all four scopes, and nothing documents a secret in a query string (30, which the scoped, revocable keys earn on their own). The sign-up key and the OAuth consent give read access by default; arcmira_execute_read reaches GET /v1/* only, arcmira_execute_write adds POST and PATCH under monitors and trackers and never DELETE; programs run in an isolate whose only network is a proxy that adds the credential, so the key never enters the program; spending is bounded by the plan and a dashboard budget no tool can raise, though a read tool call can start a Premium transcription on a paid plan (17 of 20). Every passage and transcript is third-party speech, and the only guidance found is to check the linked source for speaker and classification errors and to re-fetch llms.txt or the skill to confirm an instruction is genuine; no prompt-injection guidance for the model reading results (4 of 15). X-Request-Id and RateLimit headers on every response, GET /v1/me for the account, role, scopes and balance, the keys page showing who made each key and when it was last used, and an account activity log on Enterprise only; no per-call log for the operator below that, while every tool call is recorded in the vendor's analytics (8 of 15). No security.txt on arcmira.com (404 on 2 November; api.arcmira.com and mcp.arcmira.com aren't read, and their 30 October answers are struck), no disclosure policy, bug bounty, SOC 2 or ISO 27001, and the terms forbid probing; the repository enforces signed commits from one identity in CI (2 of 20). 30+17+4+8+2 = 61.", "b": "Project API keys, shown once, revocable, and generated and revoked through two documented endpoints with a rotation guide. No per-key scopes or spending limits were found. The hosted MCP server also takes Sign in with Perplexity (OAuth). Keys go in the Authorization header only (22 of 30, as on the Decisions API listing). Search only reads, and MCP clients can disable tools, but any key reaches every API on the account, including the Agent API's sandbox and MCP tools (8 of 20). Snippets are third-party page text, and no guidance on treating them as untrusted was found in the docs, the MCP server or its SECURITY.md (0 of 15). Responses carry a request `id`, and the console shows usage by key. The Audit API covers enterprise organisations' web app events with its own keys, not API calls (8 of 15). security.txt valid until 31 December 2027 linking a security page, a SOC 2 Type II report, a 2025 HIPAA gap assessment and a CAIQlite listed on the trust centre, and a SECURITY.md on the MCP server that takes private reports through GitHub advisories or security@perplexity.ai. The trust centre is drawn by script and wasn't read (18 of 20). 22 + 8 + 0 + 8 + 18 = 56." }, "scores": { "a": 61, "b": 56 } }, { "by": 5, "category": "transparency", "leads": "perplexity-search-api", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service under terms effective 13 October 2026 that name Arcmira, Inc., San Francisco, California law and AAA arbitration; the MCP server's source is public under an all-rights-reserved notice, while the plugin, the TypeScript SDK and CLI and the Python SDK are Apache-2.0, and the Famous rankings are CC BY 4.0 (18 of 30). The privacy policy (effective 2 October 2026) states no retention periods, keeps limited usage and billing records after an account closes, discloses session replay and that private account data isn't used to train general models, and the MCP docs and README disclose that every tool call, including the first 4,000 characters of a program and the agent's intent, is logged to product analytics with credentials redacted and no opt-out; no DPA was found, and the terms' section 7A bars bulk use and model training on Arcmira data (14 of 30). Retirements are dated and typed in the changelog (POST /v1/trackers to 410 tracker_create_retired on 8 October, tool renames answering tool_retired), but the terms allow changes with or without notice, the quickstart says routes arrive without notice and no notice period is stated (8 of 20). The policy names service-provider categories (hosting, payment, analytics, AI processing) and US processing with other locations, and the docs name PostHog, Stripe, Cloudflare and Mintlify, but there is no subprocessor list and no data-location statement beyond the US (8 of 20). 18+14+8+8 = 48.", "b": "Closed service under terms naming Perplexity AI, Inc. and California law. The MCP server is MIT and the SDKs Apache-2.0 (18 of 30). The terms and DPA say Customer Content and personal data don't train Perplexity's models, the DPA deletes personal data within 30 days of the service ending, and the Privacy and Security page says retention varies by API and zero data retention is not the default. The DPA also says Perplexity Search may follow different data terms, which weren't found, and no retention period for search queries is stated (15 of 30). Sonar Chat Completions support ended on 27 September 2026 with a migration guide and requests reformulated rather than refused, and sonar-reasoning was removed on 15 December 2025 with a named replacement. Notices are dated by month and there is no standing notice period beyond the terms' 30 days for termination (10 of 20). A sub-processor list on the trust centre, which is drawn by script and wasn't read, ten business days' notice of new non-model subprocessors, and SCCs for EU and UK transfers. No data location is stated (8 of 20). 18 + 15 + 10 + 8 = 51." }, "scores": { "a": 61, "b": 66 } } ], "facts": [ { "a": "MCP server", "b": "HTTP API", "name": "Kind" }, { "a": "Arcmira, Inc.", "b": "Perplexity", "name": "Vendor" }, { "a": "https://mcp.arcmira.com/mcp", "b": "https://api.perplexity.ai/mcp", "name": "Hosted endpoint" }, { "a": "Streamable HTTP, HTTP", "b": "Streamable HTTP, stdio", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth or key", "name": "Auth" }, { "a": "Freemium", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under Arcmira's Terms of Service. The MCP server's source is public under an all-rights-reserved notice; the Claude Code plugin, the arcmira TypeScript SDK and CLI and the Python SDK are Apache-2.0, and the Famous rankings are CC BY 4.0", "b": "Proprietary service under the Perplexity API Terms of Service. The MCP server is MIT and the official SDKs Apache-2.0", "name": "Licence" }, { "a": "4", "b": "4", "name": "Tools exposed" }, { "a": "yes", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "io.github.arcmira/arcmira", "b": "ai.perplexity/mcp-server", "name": "MCP registry" }, { "a": "2026-10-15", "b": "2026-10-23", "name": "Last release" }, { "a": "2026-10-13", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "2026-10-02", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "yes", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "yes", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "yes", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "78 stars", "b": "none", "name": "Popularity" } ], "faq": [ { "answer": "Perplexity Search API scores 70.2 (BB) on agent readiness against Arcmira's 64.2 (B), and leads in 3 of 7 scored categories. Arcmira leads on agent ergonomics, security \u0026 auth and payments \u0026 pricing.", "question": "Which is better for AI agents, Arcmira or Perplexity Search API?" }, { "answer": "Both take an API key or an OAuth sign-in.", "question": "Do Arcmira and Perplexity Search API need an API key?" }, { "answer": "Yes. Arcmira has a hosted endpoint at https://mcp.arcmira.com/mcp and Perplexity Search API at https://api.perplexity.ai/mcp.", "question": "Can an agent call Arcmira and Perplexity Search API without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 91 against 85", "Security \u0026 auth, 61 against 56", "Payments \u0026 pricing, 55 against 25" ], "also": [ "Free to start without a card" ], "goodFor": "Agents answering what was said on YouTube shows and podcasts, who was mentioned or appeared where, which brands sponsor a show and how a name's mentions are trending, with timestamped source links, through one connection on a free monthly allowance.", "slug": "arcmira", "watchFor": "No status page, incident history or SLA was found; the terms disclaim uninterrupted service and Enterprise lists priority support without an uptime commitment" }, { "aheadOn": [ "Reliability, 80 against 40", "Transparency \u0026 trust, 66 against 61" ], "also": [ "Agent-ready, a grade of BB or better", "Runs on your own machine", "No incidents deducted, where Arcmira loses 3 points for them" ], "goodFor": "Agents on any model that need raw ranked sources with extracted text at a low per-request price, and teams that want cited answers from the same key through the Agent API.", "slug": "perplexity-search-api", "watchFor": "The FAQ says uptime and recovery time are not guaranteed, and the terms carry no SLA" } ], "history": { "arcmira": [ { "causes": [ "method" ], "date": "2026-10-30", "delta": -0.4, "from": 64.6, "fromGrade": "B", "to": 64.2, "toGrade": "B" } ], "perplexity-search-api": null }, "job": { "capability": "search.research", "name": "Research search" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-arcmira.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Arcmira", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-arcmira" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-perplexity-search-api.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-bing-grounding.json", "title": "Arcmira vs Grounding with Bing Search", "url": "https://www.anchorterminal.com/compare/arcmira-vs-bing-grounding" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-brave-search-mcp.json", "title": "Arcmira vs Brave Search API + MCP", "url": "https://www.anchorterminal.com/compare/arcmira-vs-brave-search-mcp" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-cloudflare-web-search.json", "title": "Arcmira vs Cloudflare Web Search API", "url": "https://www.anchorterminal.com/compare/arcmira-vs-cloudflare-web-search" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-deepseek-search-api.json", "title": "Arcmira vs DeepSeek Search and Fetch API", "url": "https://www.anchorterminal.com/compare/arcmira-vs-deepseek-search-api" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-firecrawl-mcp.json", "title": "Arcmira vs Firecrawl MCP", "url": "https://www.anchorterminal.com/compare/arcmira-vs-firecrawl-mcp" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-kagi-search.json", "title": "Arcmira vs Kagi Search API", "url": "https://www.anchorterminal.com/compare/arcmira-vs-kagi-search" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-mojeek.json", "title": "Arcmira vs Mojeek Web Search API", "url": "https://www.anchorterminal.com/compare/arcmira-vs-mojeek" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-searchapi-io.json", "title": "Arcmira vs SearchAPI.io", "url": "https://www.anchorterminal.com/compare/arcmira-vs-searchapi-io" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-serpapi.json", "title": "Arcmira vs SerpApi", "url": "https://www.anchorterminal.com/compare/arcmira-vs-serpapi" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-serper.json", "title": "Arcmira vs Serper", "url": "https://www.anchorterminal.com/compare/arcmira-vs-serper" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-serpkite.json", "title": "Arcmira vs SerpKite", "url": "https://www.anchorterminal.com/compare/arcmira-vs-serpkite" }, { "json": "https://www.anchorterminal.com/compare/bing-grounding-vs-perplexity-search-api.json", "title": "Grounding with Bing Search vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/bing-grounding-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-perplexity-search-api.json", "title": "Brave Search API + MCP vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/brave-search-mcp-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-perplexity-search-api.json", "title": "Cloudflare Web Search API vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/cloudflare-web-search-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-perplexity-search-api.json", "title": "DeepSeek Search and Fetch API vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/deepseek-search-api-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/exa-mcp-vs-perplexity-search-api.json", "title": "Exa API + MCP vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/exa-mcp-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-perplexity-search-api.json", "title": "Firecrawl MCP vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/firecrawl-mcp-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/kagi-search-vs-perplexity-search-api.json", "title": "Kagi Search API vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/kagi-search-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/linkup-vs-perplexity-search-api.json", "title": "Linkup vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/linkup-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/mojeek-vs-perplexity-search-api.json", "title": "Mojeek Web Search API vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/mojeek-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/newscatcher-vs-perplexity-search-api.json", "title": "NewsCatcher vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/newscatcher-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/parallel-search-api-vs-perplexity-search-api.json", "title": "Parallel Search and Task APIs vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/parallel-search-api-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-searchapi-io.json", "title": "Perplexity Search API vs SearchAPI.io", "url": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-searchapi-io" }, { "json": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-serpapi.json", "title": "Perplexity Search API vs SerpApi", "url": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-serpapi" }, { "json": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-serper.json", "title": "Perplexity Search API vs Serper", "url": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-serper" }, { "json": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-serphouse.json", "title": "Perplexity Search API vs SERPHouse", "url": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-serpkite.json", "title": "Perplexity Search API vs SerpKite", "url": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-serpkite" }, { "json": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-specstream.json", "title": "Perplexity Search API vs SpecStream", "url": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-specstream" }, { "json": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-tavily-mcp.json", "title": "Perplexity Search API vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-tinyfish-search.json", "title": "Perplexity Search API vs TinyFish Search", "url": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-tinyfish-search" }, { "json": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-valyu.json", "title": "Perplexity Search API vs Valyu", "url": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-you-com-api.json", "title": "Perplexity Search API vs You.com APIs", "url": "https://www.anchorterminal.com/compare/perplexity-search-api-vs-you-com-api" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-exa-mcp.json", "title": "Arcmira vs Exa API + MCP", "url": "https://www.anchorterminal.com/compare/arcmira-vs-exa-mcp" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-grep-ai.json", "title": "Arcmira vs Grep AI", "url": "https://www.anchorterminal.com/compare/arcmira-vs-grep-ai" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-liner-mcp.json", "title": "Arcmira vs Liner Search MCP", "url": "https://www.anchorterminal.com/compare/arcmira-vs-liner-mcp" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-linkup.json", "title": "Arcmira vs Linkup", "url": "https://www.anchorterminal.com/compare/arcmira-vs-linkup" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-newscatcher.json", "title": "Arcmira vs NewsCatcher", "url": "https://www.anchorterminal.com/compare/arcmira-vs-newscatcher" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-parallel-search-api.json", "title": "Arcmira vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/arcmira-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-specstream.json", "title": "Arcmira vs SpecStream", "url": "https://www.anchorterminal.com/compare/arcmira-vs-specstream" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-tavily-mcp.json", "title": "Arcmira vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/arcmira-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-tinyfish-search.json", "title": "Arcmira vs TinyFish Search", "url": "https://www.anchorterminal.com/compare/arcmira-vs-tinyfish-search" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-valyu.json", "title": "Arcmira vs Valyu", "url": "https://www.anchorterminal.com/compare/arcmira-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/arcmira-vs-you-com-api.json", "title": "Arcmira vs You.com APIs", "url": "https://www.anchorterminal.com/compare/arcmira-vs-you-com-api" }, { "json": "https://www.anchorterminal.com/compare/grep-ai-vs-perplexity-search-api.json", "title": "Grep AI vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/grep-ai-vs-perplexity-search-api" }, { "json": "https://www.anchorterminal.com/compare/liner-mcp-vs-perplexity-search-api.json", "title": "Liner Search MCP vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/liner-mcp-vs-perplexity-search-api" } ], "panel": null, "scores": [ { "arcmira": 40, "by": 40, "edge": "perplexity-search-api", "key": "reliability", "name": "Reliability", "perplexity-search-api": 80, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "arcmira": 87, "by": 2, "edge": "perplexity-search-api", "key": "schema", "name": "Schema \u0026 documentation", "perplexity-search-api": 89, "weight": 13 }, { "arcmira": 91, "by": 6, "edge": "arcmira", "key": "ergonomics", "name": "Agent ergonomics", "perplexity-search-api": 85, "weight": 13 }, { "arcmira": 61, "by": 5, "edge": "arcmira", "key": "security", "name": "Security \u0026 auth", "perplexity-search-api": 56, "weight": 14 }, { "arcmira": 55, "by": 30, "edge": "arcmira", "key": "payments", "name": "Payments \u0026 pricing", "perplexity-search-api": 25, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "arcmira": 84, "by": 2, "edge": "arcmira", "key": "maintenance", "name": "Maintenance \u0026 community", "perplexity-search-api": 82, "weight": 7 }, { "arcmira": 61, "by": 5, "edge": "perplexity-search-api", "key": "transparency", "name": "Transparency \u0026 trust", "perplexity-search-api": 66, "weight": 7 } ], "summary": "Perplexity Search API scores 70.2 (BB) on agent readiness against Arcmira's 64.2 (B), and leads in 3 of 7 scored categories. Arcmira leads on agent ergonomics, security \u0026 auth and payments \u0026 pricing. Both do research search.", "tasks": null, "tutorials": [], "verdicts": { "arcmira": "Four code-mode tools over a documented v1 API, OAuth with four scopes, a read-only sign-up key from two API calls and no card, and a 1,000-credit free month. No status page, SLA or security.txt, breaking v1 changes shipped in October with same-day notice, the server is at 0.10.7, and the index covers the shows Arcmira transcribes.", "perplexity-search-api": "Raw ranked results with token-capped page text from Perplexity's own index, $5 per 1,000 requests or $1 with Fast Search, an OpenAPI description and a hosted MCP server with read-only annotations. Uptime is not guaranteed, there is no free allowance, keys carry no scopes, and no guidance on untrusted page text was found." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/arcmira-vs-perplexity-search-api", "json": "https://www.anchorterminal.com/compare/arcmira-vs-perplexity-search-api.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/arcmira-vs-perplexity-search-api.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/arcmira-vs-perplexity-search-api.min.md" }, "markdown": "Perplexity Search API scores 70.2 (BB) on agent readiness against Arcmira's 64.2 (B), and leads in 3 of 7 scored categories. Arcmira leads on agent ergonomics, security \u0026 auth and payments \u0026 pricing. Both do research search.\n\n- Arcmira: grade B, 64.2/100, rank #483 of 1510. Markdown https://www.anchorterminal.com/tools/arcmira.md · JSON https://www.anchorterminal.com/api/v1/tools/arcmira.json\n- Perplexity Search API: grade BB, 70.2/100, rank #211 of 1510. Markdown https://www.anchorterminal.com/tools/perplexity-search-api.md · JSON https://www.anchorterminal.com/api/v1/tools/perplexity-search-api.json\n- Best web search APIs for AI agents: https://www.anchorterminal.com/best/search/index.md\n- All 326 search comparisons: https://www.anchorterminal.com/compare/search/index.md\n\n## Which one, for what\n\n### Arcmira (B)\n\nGood for: Agents answering what was said on YouTube shows and podcasts, who was mentioned or appeared where, which brands sponsor a show and how a name's mentions are trending, with timestamped source links, through one connection on a free monthly allowance.\n\nAhead on:\n- Agent ergonomics, 91 against 85\n- Security \u0026 auth, 61 against 56\n- Payments \u0026 pricing, 55 against 25\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: No status page, incident history or SLA was found; the terms disclaim uninterrupted service and Enterprise lists priority support without an uptime commitment\n\n### Perplexity Search API (BB)\n\nGood for: Agents on any model that need raw ranked sources with extracted text at a low per-request price, and teams that want cited answers from the same key through the Agent API.\n\nAhead on:\n- Reliability, 80 against 40\n- Transparency \u0026 trust, 66 against 61\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Runs on your own machine\n- No incidents deducted, where Arcmira loses 3 points for them\n\nWatch for: The FAQ says uptime and recovery time are not guaranteed, and the terms carry no SLA\n\n\n## Why the edge\n\n### Reliability: Perplexity Search API +40\n\n- Arcmira (40): Hosted reading, for the MCP server with the HTTP API it fronts. No public status page was found on 2 November. None is linked from the docs, llms.txt, developers.md or the footer, https://arcmira.com/status answers 403 and status.arcmira.com does not resolve (0). No readable incident history, so the floor (5). Limits are published with numbers on the Plans and usage page, 60 requests a minute per key on Free, 240 on paid plans and 600 on Enterprise, with RateLimit-Limit, RateLimit-Remaining and RateLimit-Reset on every authenticated response and a 30-a-minute cap on bad keys per address (15). 429 rate_limited carries Retry-After and retry_after_seconds, developers.md asks for exponential backoff, 503 search_unavailable and transcript_fetching carry Retry-After, every POST and PATCH takes an Idempotency-Key that replays with Idempotency-Replayed, a repeated Premium read is never charged twice, and a webhook secret can be recovered under its key for 24 hours (15). No SLA. The terms (effective 13 October 2026) disclaim uninterrupted or error-free service, and the Enterprise page lists priority support but no uptime commitment (0). The HTTP API is /v1 at document version 1.0.0 with nothing labelled beta, but the MCP server agents connect to is 0.10.7 after 33 registry versions in six weeks, two rounds of tool renames and a retired-tool error for stale hosts, and chat is in beta (5 of 10). 0+5+15+15+0+5 = 40.\n- Perplexity Search API (80): Graded on the hosted lines, for `POST /search` and the hosted MCP server. status.perplexity.com, on incident.io since 10 September 2026, has an API component with an RSS feed and a JSON summary. There is no separate Search component (20). In the 90 days from 8 August the feed lists 'Investigating API issue' on 13 August, resolved with no detail, a usage-based billing issue on 3 September, and on 9 October elevated errors on the website, app and Computer, where the API 'remained operational throughout'. Minor only, with the caveat that history before the migration may be incomplete (20). The Search API is limited to 50 query units a second with a burst of 50 on every tier, and the other APIs publish QPS and token limits per tier (15). 429 carries Retry-After and an `error.type`, the SDKs retry 429 and 5xx twice honouring Retry-After, the Search best-practices page shows backoff, and failed or rate-limited searches are not billed. Searches have no side effects (15). The FAQ says Perplexity does not guarantee uptime, failure frequency or recovery time, and the terms carry no SLA (0). No beta label on the Search API, launched on 25 September 2025 (10). 20 + 20 + 15 + 15 + 0 + 10 = 80.\n\n### Payments \u0026 pricing: Arcmira +30\n\n- Arcmira (55): No x402, MPP or L402 in the OpenAPI file, llms.txt, developers.md, the docs or the pricing page (0). Prices published without a login, in credits per read (4 a passage, mention or list row past the first 5 of a request, 10 a momentum call, 40 a sponsor row, 25 an alert, 4 per started 15 minutes of captions, 300 per started 15 minutes of a Premium transcript) and in dollars (Pro $20 for 20,000 credits, Pro+ $60 for 60,000, Ultra $200 for 400,000, on-demand $0.002 a credit) (20). Free plan with 1,000 credits a month, 2 monitored names and no card, per the pricing FAQ; the 7-day Pro trial needs a card (20). POST /v1/signups with an email and POST /v1/signups/verify with the six-digit code return a read-scoped key with no browser, so an agent with a mailbox can onboard itself; the code still has to be read from an inbox, and write scopes need a dashboard key or OAuth consent (15 of 20). 0+20+20+15 = 55.\n- Perplexity Search API (25): No x402, MPP or L402 in the docs, pricing page, OpenAPI or llms.txt (0). $5 per 1,000 successful requests, $1 with Fast Search, published without a login, with failed and rate-limited requests not billed (20). Usage is prepaid with a card on the billing page, and no free allowance was found. The console playground needs no key but is a page for a person, not an API allowance (0). A person signs up in the console. The Stripe Projects route provisions a project, key and credits from a terminal, but needs a person's Stripe account with a payment method and a $10 minimum purchase (5 of 20, as on the Decisions API listing). 0 + 20 + 0 + 5 = 25.\n\n### Agent ergonomics: Arcmira +6\n\n- Arcmira (91): MCP reading. Four tools whose definitions are short, but arcmira_describe returns a reference the vendor measures at 23,124 characters, loaded once a session, and the server instructions run to 1,995 characters; the vendor's own measurement for the change to code mode was 1,123 tokens of definitions against 8,163 for the earlier ten tools (18 of 25). limit 1 to 20 on search (default 5), cursors and has_more on lists, after and before windows, about, by, kind, channel and entity filters, start and end on transcripts, and program output capped at 12,000 characters, 3,000 per string and 100 per array, so a program returns only the fields an answer needs (20). One error envelope with a stable code, a message, param, gate, unlock.url, details.limit, retry_after_seconds and request_id, surfaced to the model with isError and the call_id to report (20). Idempotency-Key on every POST and PATCH with a replay header, a Premium read that is never charged twice, writes that pause rather than delete, and all four annotations declared on every tool; arcmira_execute_read is marked not read-only because a Premium read can start a transcription that uses credits, which a strict host may treat as a write (18 of 20). Few required inputs (one search string, ids resolved for free), a 90-day default window, defaults on limit, and official Apache-2.0 SDKs for TypeScript (npm arcmira 0.6.2) and Python (pip arcmira, repository v0.6.2) plus a CLI, with the caveat that the MCP client's argument names differ from the HTTP and SDK names (15). 18+20+20+18+15 = 91.\n- Perplexity Search API (85): `max_results` 1 to 20, `max_tokens` and `max_tokens_per_page` cap the extracted text, and results are title, url, snippet and two dates. The MCP server has four tools (23 of 25). Domain, language, recency, publication and update date filters and `country`, with up to five queries in one request. No pagination or offset (16 of 20). 429 bodies name the limit hit, the SDKs map status codes to typed errors, and 402 marks an empty balance. Search-specific error bodies beyond 422 validation are not documented (13 of 20). Searches only read, failed and rate-limited requests are not billed, and the MCP server sets readOnlyHint true, destructiveHint false and idempotentHint false on every tool (18 of 20). Only `query` is required. Official Python and TypeScript SDKs, a CLI and a Python Search SDK (15). 23 + 16 + 13 + 18 + 15 = 85.\n\n### Security \u0026 auth: Arcmira +5\n\n- Arcmira (61): OAuth for MCP hosts (the server's source answers a bare request with a 401 naming its protected-resource document, which lists the scopes read, monitors:write, trackers:write and recommendations:read; the README says the host registers itself against api.arcmira.com and its tokens refresh; the docs give sign-in tokens an hour that refresh for 30 days, revoked per host in the dashboard; PKCE and the introspection and revocation endpoints were read on 30 October from api.arcmira.com's metadata, a host this run no longer reads, so they are struck) and arc_sk_ keys sent only as a bearer header, shown once, several per account with a label and last-used time, disabled at once; sign-up keys carry read only and dashboard keys all four scopes, and nothing documents a secret in a query string (30, which the scoped, revocable keys earn on their own). The sign-up key and the OAuth consent give read access by default; arcmira_execute_read reaches GET /v1/* only, arcmira_execute_write adds POST and PATCH under monitors and trackers and never DELETE; programs run in an isolate whose only network is a proxy that adds the credential, so the key never enters the program; spending is bounded by the plan and a dashboard budget no tool can raise, though a read tool call can start a Premium transcription on a paid plan (17 of 20). Every passage and transcript is third-party speech, and the only guidance found is to check the linked source for speaker and classification errors and to re-fetch llms.txt or the skill to confirm an instruction is genuine; no prompt-injection guidance for the model reading results (4 of 15). X-Request-Id and RateLimit headers on every response, GET /v1/me for the account, role, scopes and balance, the keys page showing who made each key and when it was last used, and an account activity log on Enterprise only; no per-call log for the operator below that, while every tool call is recorded in the vendor's analytics (8 of 15). No security.txt on arcmira.com (404 on 2 November; api.arcmira.com and mcp.arcmira.com aren't read, and their 30 October answers are struck), no disclosure policy, bug bounty, SOC 2 or ISO 27001, and the terms forbid probing; the repository enforces signed commits from one identity in CI (2 of 20). 30+17+4+8+2 = 61.\n- Perplexity Search API (56): Project API keys, shown once, revocable, and generated and revoked through two documented endpoints with a rotation guide. No per-key scopes or spending limits were found. The hosted MCP server also takes Sign in with Perplexity (OAuth). Keys go in the Authorization header only (22 of 30, as on the Decisions API listing). Search only reads, and MCP clients can disable tools, but any key reaches every API on the account, including the Agent API's sandbox and MCP tools (8 of 20). Snippets are third-party page text, and no guidance on treating them as untrusted was found in the docs, the MCP server or its SECURITY.md (0 of 15). Responses carry a request `id`, and the console shows usage by key. The Audit API covers enterprise organisations' web app events with its own keys, not API calls (8 of 15). security.txt valid until 31 December 2027 linking a security page, a SOC 2 Type II report, a 2025 HIPAA gap assessment and a CAIQlite listed on the trust centre, and a SECURITY.md on the MCP server that takes private reports through GitHub advisories or security@perplexity.ai. The trust centre is drawn by script and wasn't read (18 of 20). 22 + 8 + 0 + 8 + 18 = 56.\n\n### Transparency \u0026 trust: Perplexity Search API +5\n\n- Arcmira (61): Closed service under terms effective 13 October 2026 that name Arcmira, Inc., San Francisco, California law and AAA arbitration; the MCP server's source is public under an all-rights-reserved notice, while the plugin, the TypeScript SDK and CLI and the Python SDK are Apache-2.0, and the Famous rankings are CC BY 4.0 (18 of 30). The privacy policy (effective 2 October 2026) states no retention periods, keeps limited usage and billing records after an account closes, discloses session replay and that private account data isn't used to train general models, and the MCP docs and README disclose that every tool call, including the first 4,000 characters of a program and the agent's intent, is logged to product analytics with credentials redacted and no opt-out; no DPA was found, and the terms' section 7A bars bulk use and model training on Arcmira data (14 of 30). Retirements are dated and typed in the changelog (POST /v1/trackers to 410 tracker_create_retired on 8 October, tool renames answering tool_retired), but the terms allow changes with or without notice, the quickstart says routes arrive without notice and no notice period is stated (8 of 20). The policy names service-provider categories (hosting, payment, analytics, AI processing) and US processing with other locations, and the docs name PostHog, Stripe, Cloudflare and Mintlify, but there is no subprocessor list and no data-location statement beyond the US (8 of 20). 18+14+8+8 = 48.\n- Perplexity Search API (66): Closed service under terms naming Perplexity AI, Inc. and California law. The MCP server is MIT and the SDKs Apache-2.0 (18 of 30). The terms and DPA say Customer Content and personal data don't train Perplexity's models, the DPA deletes personal data within 30 days of the service ending, and the Privacy and Security page says retention varies by API and zero data retention is not the default. The DPA also says Perplexity Search may follow different data terms, which weren't found, and no retention period for search queries is stated (15 of 30). Sonar Chat Completions support ended on 27 September 2026 with a migration guide and requests reformulated rather than refused, and sonar-reasoning was removed on 15 December 2025 with a named replacement. Notices are dated by month and there is no standing notice period beyond the terms' 30 days for termination (10 of 20). A sub-processor list on the trust centre, which is drawn by script and wasn't read, ten business days' notice of new non-model subprocessors, and SCCs for EU and UK transfers. No data location is stated (8 of 20). 18 + 15 + 10 + 8 = 51.\n\n## Score by category\n\n| Category | Weight | Arcmira | Perplexity Search API | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 40 | 80 | Perplexity Search API +40 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 87 | 89 | Perplexity Search API +2 |\n| Agent ergonomics | 13% (16.2 this run) | 91 | 85 | Arcmira +6 |\n| Security \u0026 auth | 14% (17.5 this run) | 61 | 56 | Arcmira +5 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 55 | 25 | Arcmira +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 84 | 82 | Arcmira +2 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 61 | 66 | Perplexity Search API +5 |\n| Negative events | ≤15 | -3 | 0 | |\n| **Total** | | **64.2 · B** | **70.2 · BB** | |\n\n## Facts side by side\n\n| Fact | Arcmira | Perplexity Search API |\n| --- | --- | --- |\n| Kind | MCP server | HTTP API |\n| Vendor | Arcmira, Inc. | Perplexity |\n| Hosted endpoint | `https://mcp.arcmira.com/mcp` | `https://api.perplexity.ai/mcp` |\n| Transports | Streamable HTTP, HTTP | Streamable HTTP, stdio |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Freemium | Pay per use |\n| x402 | no | no |\n| Licence | Proprietary service under Arcmira's Terms of Service. The MCP server's source is public under an all-rights-reserved notice; the Claude Code plugin, the arcmira TypeScript SDK and CLI and the Python SDK are Apache-2.0, and the Famous rankings are CC BY 4.0 | Proprietary service under the Perplexity API Terms of Service. The MCP server is MIT and the official SDKs Apache-2.0 |\n| Tools exposed | 4 | 4 |\n| Read-only variant documented | yes | no |\n| llms.txt | yes | yes |\n| MCP registry | `io.github.arcmira/arcmira` | `ai.perplexity/mcp-server` |\n| Last release | 2026-10-15 | 2026-10-23 |\n| Terms last updated | 2026-10-13 | couldn't be read |\n| Privacy policy last updated | 2026-10-02 | couldn't be read |\n| Customer content may train models | yes | couldn't be read |\n| Terms restrict automated access | yes | couldn't be read |\n| Terms restrict benchmarking | yes | couldn't be read |\n| Terms or service can change without notice | yes | couldn't be read |\n| Arbitration or class-action waiver | yes | couldn't be read |\n| Popularity | 78 stars | none |\n\n## How the scores have moved\n\n### Arcmira\n\n- -0.4 on 30 October 2026: checklist\n\n### Perplexity Search API\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Arcmira.** Four code-mode tools over a documented v1 API, OAuth with four scopes, a read-only sign-up key from two API calls and no card, and a 1,000-credit free month. No status page, SLA or security.txt, breaking v1 changes shipped in October with same-day notice, the server is at 0.10.7, and the index covers the shows Arcmira transcribes.\n\n**Perplexity Search API.** Raw ranked results with token-capped page text from Perplexity's own index, $5 per 1,000 requests or $1 with Fast Search, an OpenAPI description and a hosted MCP server with read-only annotations. Uptime is not guaranteed, there is no free allowance, keys carry no scopes, and no guidance on untrusted page text was found.\n\n## Before you call either\n\n### Arcmira\n\n1. Call `arcmira_describe` once per session and write one program per question for `arcmira_execute_read`; return only the fields the answer needs, since output is cut at 12,000 characters and 3,000 per string.\n2. Resolve names with `arcmira.resolve` (free) before any `about`, `by`, `entity_ids` or `channel` filter; a name in a filter fails with `id_required`. Plain keyword search needs no resolver call.\n3. Check `arcmira.status()` or GET /v1/me for the plan, scopes and `usage.credits.available` before metered reads; on Free, media newer than 30 days and pages past the first fail with `freshness_requires_paid` and `pagination_gated`.\n4. A Premium read of an untranscribed video starts a transcription that uses credits (300 per started 15 minutes) and may return `pending`; read the same video again later, which is never charged twice, and send `retry: true` only when the user asks.\n5. Over HTTP send `Authorization: Bearer arc_sk_...`, an `Idempotency-Key` on every POST and PATCH, honour `Retry-After` on 429, and switch on `error.code`, following `unlock.url` on 402 and 403 rather than re-authenticating.\n6. Use `arcmira_execute_write` only after listing the user's monitors; it creates, follows and pauses but never deletes, and a connection made before server 0.9.0 answers `insufficient_scope` until reconnected.\n\n### Perplexity Search API\n\n1. Set `max_tokens_per_page` and `max_tokens` before calling; extracted text otherwise fills the context, and the price does not change with size\n2. Skip results with an empty `snippet` and dedupe by `url` when sending a `query` array; each query costs one rate-limit unit\n3. Use `search_type: \"fast\"` for $1 per 1,000 when latency and cost matter more than depth\n4. On 429 wait for Retry-After, then back off; on 402 stop and ask the user to add credits\n5. Use the Search API for sources and the Agent API's web_search tool for a written answer with citations\n\n## Questions\n\n### Which is better for AI agents, Arcmira or Perplexity Search API?\n\nPerplexity Search API scores 70.2 (BB) on agent readiness against Arcmira's 64.2 (B), and leads in 3 of 7 scored categories. Arcmira leads on agent ergonomics, security \u0026 auth and payments \u0026 pricing.\n\n### Do Arcmira and Perplexity Search API need an API key?\n\nBoth take an API key or an OAuth sign-in.\n\n### Can an agent call Arcmira and Perplexity Search API without installing anything?\n\nYes. Arcmira has a hosted endpoint at https://mcp.arcmira.com/mcp and Perplexity Search API at https://api.perplexity.ai/mcp.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/arcmira-vs-perplexity-search-api.json, and with the fewest tokens: https://www.anchorterminal.com/compare/arcmira-vs-perplexity-search-api.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"arcmira\", \"b\": \"perplexity-search-api\"}`. From a terminal: `anchor compare arcmira perplexity-search-api`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/arcmira.json and https://www.anchorterminal.com/api/v1/tools/perplexity-search-api.json\n\n## Other comparisons with Arcmira or Perplexity Search API\n\n- [Web Search Tool on Amazon Bedrock AgentCore vs Arcmira](https://www.anchorterminal.com/compare/agentcore-web-search-vs-arcmira.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Perplexity Search API](https://www.anchorterminal.com/compare/agentcore-web-search-vs-perplexity-search-api.md)\n- [Arcmira vs Grounding with Bing Search](https://www.anchorterminal.com/compare/arcmira-vs-bing-grounding.md)\n- [Arcmira vs Brave Search API + MCP](https://www.anchorterminal.com/compare/arcmira-vs-brave-search-mcp.md)\n- [Arcmira vs Cloudflare Web Search API](https://www.anchorterminal.com/compare/arcmira-vs-cloudflare-web-search.md)\n- [Arcmira vs DeepSeek Search and Fetch API](https://www.anchorterminal.com/compare/arcmira-vs-deepseek-search-api.md)\n- [Arcmira vs Firecrawl MCP](https://www.anchorterminal.com/compare/arcmira-vs-firecrawl-mcp.md)\n- [Arcmira vs Kagi Search API](https://www.anchorterminal.com/compare/arcmira-vs-kagi-search.md)\n- [Arcmira vs Mojeek Web Search API](https://www.anchorterminal.com/compare/arcmira-vs-mojeek.md)\n- [Arcmira vs SearchAPI.io](https://www.anchorterminal.com/compare/arcmira-vs-searchapi-io.md)\n- [Arcmira vs SerpApi](https://www.anchorterminal.com/compare/arcmira-vs-serpapi.md)\n- [Arcmira vs Serper](https://www.anchorterminal.com/compare/arcmira-vs-serper.md)\n- [Arcmira vs SerpKite](https://www.anchorterminal.com/compare/arcmira-vs-serpkite.md)\n- [Grounding with Bing Search vs Perplexity Search API](https://www.anchorterminal.com/compare/bing-grounding-vs-perplexity-search-api.md)\n- [Brave Search API + MCP vs Perplexity Search API](https://www.anchorterminal.com/compare/brave-search-mcp-vs-perplexity-search-api.md)\n- [Cloudflare Web Search API vs Perplexity Search API](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-perplexity-search-api.md)\n- [DeepSeek Search and Fetch API vs Perplexity Search API](https://www.anchorterminal.com/compare/deepseek-search-api-vs-perplexity-search-api.md)\n- [Exa API + MCP vs Perplexity Search API](https://www.anchorterminal.com/compare/exa-mcp-vs-perplexity-search-api.md)\n- [Firecrawl MCP vs Perplexity Search API](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-perplexity-search-api.md)\n- [Kagi Search API vs Perplexity Search API](https://www.anchorterminal.com/compare/kagi-search-vs-perplexity-search-api.md)\n- [Linkup vs Perplexity Search API](https://www.anchorterminal.com/compare/linkup-vs-perplexity-search-api.md)\n- [Mojeek Web Search API vs Perplexity Search API](https://www.anchorterminal.com/compare/mojeek-vs-perplexity-search-api.md)\n- [NewsCatcher vs Perplexity Search API](https://www.anchorterminal.com/compare/newscatcher-vs-perplexity-search-api.md)\n- [Parallel Search and Task APIs vs Perplexity Search API](https://www.anchorterminal.com/compare/parallel-search-api-vs-perplexity-search-api.md)\n- [Perplexity Search API vs SearchAPI.io](https://www.anchorterminal.com/compare/perplexity-search-api-vs-searchapi-io.md)\n- [Perplexity Search API vs SerpApi](https://www.anchorterminal.com/compare/perplexity-search-api-vs-serpapi.md)\n- [Perplexity Search API vs Serper](https://www.anchorterminal.com/compare/perplexity-search-api-vs-serper.md)\n- [Perplexity Search API vs SERPHouse](https://www.anchorterminal.com/compare/perplexity-search-api-vs-serphouse.md)\n- [Perplexity Search API vs SerpKite](https://www.anchorterminal.com/compare/perplexity-search-api-vs-serpkite.md)\n- [Perplexity Search API vs SpecStream](https://www.anchorterminal.com/compare/perplexity-search-api-vs-specstream.md)\n- [Perplexity Search API vs Tavily API + MCP](https://www.anchorterminal.com/compare/perplexity-search-api-vs-tavily-mcp.md)\n- [Perplexity Search API vs TinyFish Search](https://www.anchorterminal.com/compare/perplexity-search-api-vs-tinyfish-search.md)\n- [Perplexity Search API vs Valyu](https://www.anchorterminal.com/compare/perplexity-search-api-vs-valyu.md)\n- [Perplexity Search API vs You.com APIs](https://www.anchorterminal.com/compare/perplexity-search-api-vs-you-com-api.md)\n- [Arcmira vs Exa API + MCP](https://www.anchorterminal.com/compare/arcmira-vs-exa-mcp.md)\n- [Arcmira vs Grep AI](https://www.anchorterminal.com/compare/arcmira-vs-grep-ai.md)\n- [Arcmira vs Liner Search MCP](https://www.anchorterminal.com/compare/arcmira-vs-liner-mcp.md)\n- [Arcmira vs Linkup](https://www.anchorterminal.com/compare/arcmira-vs-linkup.md)\n- [Arcmira vs NewsCatcher](https://www.anchorterminal.com/compare/arcmira-vs-newscatcher.md)\n- [Arcmira vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/arcmira-vs-parallel-search-api.md)\n- [Arcmira vs SpecStream](https://www.anchorterminal.com/compare/arcmira-vs-specstream.md)\n- [Arcmira vs Tavily API + MCP](https://www.anchorterminal.com/compare/arcmira-vs-tavily-mcp.md)\n- [Arcmira vs TinyFish Search](https://www.anchorterminal.com/compare/arcmira-vs-tinyfish-search.md)\n- [Arcmira vs Valyu](https://www.anchorterminal.com/compare/arcmira-vs-valyu.md)\n- [Arcmira vs You.com APIs](https://www.anchorterminal.com/compare/arcmira-vs-you-com-api.md)\n- [Grep AI vs Perplexity Search API](https://www.anchorterminal.com/compare/grep-ai-vs-perplexity-search-api.md)\n- [Liner Search MCP vs Perplexity Search API](https://www.anchorterminal.com/compare/liner-mcp-vs-perplexity-search-api.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Arcmira vs Perplexity Search API", "url": "" } ], "description": "Perplexity Search scores 70.2 (BB) to Arcmira's 64.2 (B) for research search. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Arcmira B 64.2", "Perplexity Search API BB 70.2", "scores" ], "h1": "Arcmira vs Perplexity Search API", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/arcmira-vs-perplexity-search-api", "published": "2026-10-01", "section": "tools", "title": "Arcmira vs Perplexity Search for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/arcmira-vs-perplexity-search-api" }, "tokens": { "markdown": 6850, "slim": 4130 }, "version": 1 }