{ "data": { "a": { "slug": "agentcore-web-search", "name": "Web Search Tool on Amazon Bedrock AgentCore", "vendor": "Amazon Web Services", "vendorUrl": "https://aws.amazon.com/bedrock/agentcore/", "kind": "mcp", "category": "search", "summary": "Web Search Tool on Amazon Bedrock AgentCore is AWS's managed web search for agents, backed by an Amazon-operated index and knowledge graph. It runs as a connector on an AgentCore Gateway and is called as an MCP tool.", "url": "https://www.anchorterminal.com/tools/agentcore-web-search", "markdownUrl": "https://www.anchorterminal.com/tools/agentcore-web-search.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/agentcore-web-search.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/agentcore-web-search.json", "dns": "agentcore-web-search.grade.anchorterminal.com", "license": "Proprietary service under the AWS Customer Agreement and Service Terms, with an acceptable-use section on the tool's documentation page", "transports": [ "streamable-http" ], "remoteUrl": "https://{gateway-id}.gateway.bedrock-agentcore.{region}.amazonaws.com/mcp", "packages": [], "auth": "mixed", "authNotes": "Calls go to the owner's AgentCore Gateway, which takes OAuth JWT bearer tokens from a configured identity provider with allowed scopes, or IAM SigV4 with `bedrock-agentcore:InvokeGateway` on the gateway ARN. A no-authorisation mode exists, which AWS says not to use in production. The gateway's service role needs `bedrock-agentcore:InvokeWebSearch` on `arn:aws:bedrock-agentcore:\u003cregion\u003e:aws:tool/web-search.v1`. The agent holds no search credentials. Self-serve once an AWS account exists, with no partner or sales approval.", "pricing": "usage", "pricingNotes": "$7.00 per 1,000 queries, billed per query with no minimum, plus the Gateway's $0.005 per 1,000 invocations for each `tools/call`. No allowance specific to Web Search. New AWS accounts get up to $200 in Free Tier credits, and the Free Tier FAQ says a payment method isn't required to sign up for most new customers (https://aws.amazon.com/bedrock/agentcore/pricing/, https://aws.amazon.com/free/free-tier-faqs/, checked 2026-10-17).", "priceSummary": "$7 / 1k req", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the Gateway or the Web Search Tool, in the docs or on the pricing page. AgentCore payments, a separate component, lets a customer's agents pay third parties over x402 and MPP and is not a way to pay AWS (checked 2026-10-17).", "endpoints": [] }, "toolCount": 1, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-17" }, "docsUrl": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-target-connector-web-search-tool.html", "llmsTxt": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/llms.txt", "capabilities": [ "web.search" ], "tags": [ "hosted", "usage-priced", "closed-source", "enterprise", "llms-txt", "mcp", "free-tier", "no-card", "status-page", "soc2" ], "lastRelease": "2026-10-19", "graded": true, "anchor": { "graded": true, "score": 75.2, "grade": "BB", "agentReady": true, "rank": 70, "ranked": true, "rankOf": 1510, "categoryRank": 3, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 80, "payments": 30, "reliability": 90, "schema": 78, "security": 85, "transparency": 77 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "One compact MCP tool returns ranked snippets with URLs, titles and published dates from an Amazon-operated index, with domain and date filters and a read-only annotation on the default connector, at $7 per 1,000 queries. A first call needs an AWS account, a Gateway with inbound auth, a target and a service role, and tool errors are not documented.", "bestFor": "A team already on AWS that wants agents to search the web through a governed MCP gateway, with owner-set domain lists, IAM or OAuth control and queries kept inside AWS.", "strengths": [ "One tool with three inputs, `query`, `maxResults` and `filters`, of which only `query` is required, returning snippet text, URL, title and published date", "Domain include and exclude lists of up to 100 domains, set by the owner on the target, which the agent cannot relax, and per request from connector 1.2.0 with published-date bounds", "$7.00 per 1,000 queries is published without a login, plus $0.005 per 1,000 Gateway invocations", "Gateway inbound auth is OAuth JWT with allowed scopes or IAM SigV4, and the service role's `InvokeWebSearch` permission names one service-owned ARN", "Connector versions follow semver with release dates and a lifecycle from available to retired, and the default 1.3.0 marks the tool `readOnlyHint` for MCP clients" ], "weaknesses": [ "No error responses for the tool are documented. The only response example has `isError` false", "Targets created before 19 October 2026 keep their pinned version, so they lack the 1.3.0 annotations, and on 1.1.0 the request-level filters, until updated", "Available in seven Regions, four of them added on 15 October 2026", "Results are third-party page text, and the Web Search pages give no prompt-injection guidance. Gateway guardrail policies are documented separately", "No retention period for queries was found. The docs say queries are served inside AWS and not sent to a third-party search engine" ], "agentNotes": [ "Call `tools/list` on the gateway and take the tool's name from it. AWS's call examples name gateway tools by target and tool", "Keep `query` to 200 characters and `maxResults` between 1 and 25 (default 10). The published schema states these limits only in descriptions", "Check the target's connector version before sending `filters`. Version 1.1.0 exposes only `query` and `maxResults`; 1.2.0 and the default 1.3.0 take filters", "Keep each result's URL and title with any answer built from it. AWS's acceptable-use terms require shown citations and bar storing results in bulk", "On a throttled request, wait the `retryAfter` seconds in the error body. The default quota is 10 Web Search requests a second, adjustable" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 75.2 } ], "editorialScores": { "ergonomics": 75, "maintenance": 80, "payments": 30, "reliability": 90, "schema": 78, "security": 85, "transparency": 60 }, "provenanceScore": 94, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "agentcore add gateway-target --name MyWebSearchTarget --type connector --connector web-search --gateway MyGateway \u0026\u0026 agentcore deploy", "http": "curl -X POST \"https://$GATEWAY_ID.gateway.bedrock-agentcore.us-east-1.amazonaws.com/mcp\" \\\n -H \"Accept: application/json, text/event-stream\" \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $ACCESS_TOKEN\" \\\n -H \"MCP-Protocol-Version: 2025-11-25\" \\\n -d '{\"jsonrpc\":\"2.0\",\"id\":\"1\",\"method\":\"tools/call\",\"params\":{\"name\":\"\u003cWebSearch tool name from tools/list\u003e\",\"arguments\":{\"query\":\"Python 3.13 release date\",\"maxResults\":5}}}'" }, "letme": { "capability": "https://letme.dev/web.search", "tool": "https://letme.dev/agentcore-web-search" }, "sameCompany": [ "amazon-bedrock", "amazon-nova-embeddings", "amazon-bedrock-guardrails", "amazon-transcribe", "amazon-polly", "amazon-nova-sonic", "agentcore-memory", "agentcore-identity", "aws-secrets-manager", "aws-mcp-servers", "amazon-ses", "amazon-location", "amazon-translate", "amazon-ads-api", "amazon-creators-api" ], "area": "web-data", "unitPrices": [ { "item": "Search query", "unit": "1k-requests", "usd": 7, "note": "Plus $0.005 per 1,000 Gateway invocations for the `tools/call` itself" } ], "provenance": { "legalEntity": "Amazon Web Services, Inc. (regional AWS entities by account location)", "domain": "amazon.com", "domainRegistered": "1994-11-01", "domainNote": "The service pages are under aws.amazon.com and the gateway endpoints on amazonaws.com, an AWS domain. The registration date is the one on our other AWS listings and was not looked up again on 17 October 2026.", "endpointOnVendorDomain": true, "terms": "https://aws.amazon.com/service-terms/", "privacy": "https://aws.amazon.com/privacy/", "statusPage": "https://health.aws.amazon.com/health/status", "changelog": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/release-notes.html", "securityTxt": "valid", "checked": "2026-11-01", "notes": [ "aws.amazon.com/.well-known/security.txt carries Expires 2027-10-16T16:25:03.000Z, re-read on 1 November 2026. It points to the vulnerability disclosure programme on HackerOne and the policy at vdp.aws.security.", "The AWS Service Terms show Last Updated 30 October 2026. No clause names Web Search, and section 50.3, which lets AWS use content from named AI services for improvement, does not list Bedrock or AgentCore, per this run's AgentCore Memory and Identity re-checks of the same day.", "The Web Search Tool page carries its own acceptable-use section. Users must keep and show the source citations and links with any output that uses a search result, and may not extract, store or reproduce results in bulk or build a competing index.", "The AWS Privacy Notice shows Last Updated 18 May 2026 and the sub-processor page 30 October 2026.", "The dashboard's history file, re-read on 1 November 2026, lists one event naming Bedrock AgentCore in the 90 days from 3 August, packet loss in one zone of eu-south-2 on 4 October 2026, a Region where Web Search is not sold.", "AgentCore release notes carry a month for each entry, not a day. Dated launches are on AWS What's New, and the connector versions page gives a release date for each version." ], "score": 94 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/agentcore-web-search.json", "live": { "slug": "agentcore-web-search", "probe": { "target": "https://{gateway-id}.gateway.bedrock-agentcore.{region}.amazonaws.com/mcp", "method": "mcp-initialize", "lastAt": "2026-11-07T19:21:50.572825492Z", "lastOk": false, "lastStatus": 0, "lastMs": 0, "lastNote": "invalid character \"{\" in host name", "authRequired": false, "uptime24h": 0, "uptime30d": 0, "p50ms24h": 0, "p95ms24h": 0, "samples24h": 238, "samples30d": 5155, "days": [ { "date": "2026-10-17", "probes": 21, "ok": 0 }, { "date": "2026-10-18", "probes": 256, "ok": 0 }, { "date": "2026-10-19", "probes": 255, "ok": 0 }, { "date": "2026-10-20", "probes": 252, "ok": 0 }, { "date": "2026-10-21", "probes": 253, "ok": 0 }, { "date": "2026-10-22", "probes": 253, "ok": 0 }, { "date": "2026-10-23", "probes": 248, "ok": 0 }, { "date": "2026-10-24", "probes": 251, "ok": 0 }, { "date": "2026-10-25", "probes": 250, "ok": 0 }, { "date": "2026-10-26", "probes": 252, "ok": 0 }, { "date": "2026-10-27", "probes": 249, "ok": 0 }, { "date": "2026-10-28", "probes": 251, "ok": 0 }, { "date": "2026-10-29", "probes": 249, "ok": 0 }, { "date": "2026-10-30", "probes": 248, "ok": 0 }, { "date": "2026-10-31", "probes": 251, "ok": 0 }, { "date": "2026-11-01", "probes": 249, "ok": 0 }, { "date": "2026-11-02", "probes": 250, "ok": 0 }, { "date": "2026-11-03", "probes": 248, "ok": 0 }, { "date": "2026-11-04", "probes": 246, "ok": 0 }, { "date": "2026-11-05", "probes": 185, "ok": 0 }, { "date": "2026-11-06", "probes": 241, "ok": 0 }, { "date": "2026-11-07", "probes": 197, "ok": 0 } ], "outages": [ { "start": "2026-10-17T22:04:33.041450753Z", "end": "0001-01-01T00:00:00Z", "note": "invalid character \"{\" in host name" } ] }, "securityTxt": { "url": "https://amazon.com/.well-known/security.txt", "state": "valid", "checkedAt": "2026-11-07T16:00:18.354437696Z" }, "llmsTxt": { "url": "https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:31:11.626288028Z" }, "domain": { "domain": "amazon.com", "registered": "1994-11-01", "source": "https://rdap.verisign.com/com/v1/domain/amazon.com", "checkedAt": "2026-11-01T14:09:08.477101866Z" }, "mcpTools": { "url": "https://{gateway-id}.gateway.bedrock-agentcore.{region}.amazonaws.com/mcp", "checkedAt": "2026-11-07T01:42:20.113143394Z", "status": "error", "note": "parse \"https://{gateway-id}.gateway.bedrock-agentcore.{region}.amazonaws.com/mcp\": invalid character \"{\" in host name", "changedAt": "2026-10-17T22:37:09.365200504Z" }, "updatedAt": "2026-11-07T19:21:50.572825492Z" } }, "answer": "Web Search Tool on Amazon Bedrock AgentCore scores 75.2 (BB) on agent readiness against Perplexity Search API's 70.2 (BB), and leads in 4 of 7 scored categories. Perplexity Search API leads on schema \u0026 documentation and agent ergonomics.", "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": 29, "category": "security", "leads": "agentcore-web-search", "name": "Security \u0026 auth", "reasons": { "a": "Gateway inbound auth is OAuth JWT from the owner's identity provider with allowed scopes advertised in the 401 challenge, or IAM SigV4 scoped to one gateway ARN, and the agent never holds a search credential (30). The tool only reads. The owner's target-level include and exclude lists cannot be relaxed by the agent, the service role's `InvokeWebSearch` names one service-owned ARN, and Cedar policies on the gateway can forbid the tool per caller. A no-authorisation gateway mode exists, with AWS's warning against production use (17 of 20). Results are third-party page text and the Web Search pages give no guidance on treating them as untrusted. Gateway guardrail policies can screen inputs for prompt attacks and suppress outputs, documented in general and not for this tool (7 of 15). CloudWatch metrics by method and tool name, and CloudTrail data events for `InvokeGateway` when the owner turns them on, at extra cost (13 of 15). A vulnerability disclosure programme on HackerOne, a security.txt that expires on 16 October 2027 (re-read on 1 November), and SOC and ISO 27001 among the programmes the AgentCore FAQ lists. No paid bounty found, so 2 held back as on every AWS listing (18 of 20).", "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": 85, "b": 56 } }, { "by": 11, "category": "schema", "leads": "perplexity-search-api", "name": "Schema \u0026 documentation", "reasons": { "a": "The tool's `inputSchema` is published in full as JSON Schema, with `query` required, and the Gateway control plane is in AWS's service models (25). The developer guide has an llms.txt of 1,024 lines on 1 November and serves every page as Markdown (10). The page explains purpose, use cases, the two filter layers and how they compose, but says nothing on when another tool fits better (12 of 20). Types are given, but the 200-character limit on `query`, the 1 to 25 range of `maxResults` and the ISO-8601 date format sit in descriptions, with no `maxLength`, `minimum`, `maximum` or `format` (9 of 15). Python, AWS CLI and AgentCore CLI set-up examples and one response example. No error responses for the tool are documented, and the June release note links to a page that now redirects to the guide's front page (7 of 15). Semver connector versions with release dates (1.3.0 on 19 October 2026), a lifecycle table, monthly release notes and dated What's New posts (15).", "b": "OpenAPI 3.1.0 at docs.perplexity.ai/openapi.json describes `POST /search` with typed request and response schemas, listed in llms.txt (25). llms.txt indexes every page, each with a Markdown twin (10). The overview says what a result holds, that snippets can be empty, when to use the Search API instead of the Agent API, and that it takes queries not URLs and does not re-fetch pages (19 of 20). `search_type` is an enum, `max_results`, `max_tokens` and `max_tokens_per_page` carry minimum and maximum, country and language codes carry lengths, and `query` is a string or an array. The recency filter is an enum in the docs, and date filters are `MM/DD/YYYY` strings (14 of 15). Python, TypeScript and cURL examples with a recorded response. The spec documents only 200 and 422 for `/search`, and status codes are listed on the SDK error-handling page and the rate-limit page rather than for Search (11 of 15). A public changelog with several entries a month, dated by month only, and an unversioned `/search` path (10 of 15). 25 + 10 + 19 + 14 + 11 + 10 = 89." }, "scores": { "a": 78, "b": 89 } }, { "by": 11, "category": "transparency", "leads": "agentcore-web-search", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service under the AWS Customer Agreement and Service Terms, updated 30 October 2026, with an acceptable-use section on the docs page (15 of 30). The docs say queries are served inside AWS and not sent to a third-party engine, the Gateway data protection notes say data is encrypted with a service key or a customer managed key, and section 50.3 of the Service Terms does not list AgentCore for content use. No retention period for queries was found (15 of 30). The connector versions page sets out stages from available to deprecated and retired and promises a migration guide for a major version, without a notice period (12 of 20). A sub-processor list updated 30 October 2026 and a per-Region availability list, and the August release note says queries stay in their Region (18 of 20).", "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": 77, "b": 66 } }, { "by": 10, "category": "reliability", "leads": "agentcore-web-search", "name": "Reliability", "reasons": { "a": "Graded on the hosted lines, for the Gateway endpoint and the connector agents call. AWS Health Dashboard with per-service, per-Region history (20). The dashboard's history file, re-read on 1 November 2026, names AgentCore in one event in the 90 days from 3 August, 2 hours 40 minutes of packet loss in one zone of eu-south-2 on 4 October 2026, marked informational and in a Region where Web Search is not sold. The us-west-2 events of 3 September and 30 October (API Gateway HTTP API) don't name AgentCore. Read as clean, as on the Memory listing (30). Quotas published and re-read on 1 November, 10 Web Search requests a second and 200 tool calls a second per gateway and per account (15). Owner-set gateway rate limits return an error body with `retryAfter` in seconds and searches have no side effects, but the response to the service's own Web Search quota is not documented (10 of 15). The AgentCore FAQ says the Amazon Bedrock SLA applies, but that SLA, last updated 4 October 2023, does not name AgentCore (5 of 10, as on the Code Interpreter listing). Generally available since 16 June 2026 (10).", "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": 90, "b": 80 } }, { "by": 10, "category": "ergonomics", "leads": "perplexity-search-api", "name": "Agent ergonomics", "reasons": { "a": "One tool with a compact schema, and results are snippets AWS says are extracted for model context. Each result comes as a JSON string in a text block and again as `structuredContent` (22 of 25). `maxResults` 1 to 25, per-request domain include and exclude lists and published-date bounds from 1.2.0. No pagination, offset, country or language controls (15 of 20). JWT failures return 401 or 403 with a `WWW-Authenticate` header naming the scopes, and throttling returns `retryAfter`, but no error codes for the tool itself are documented (10 of 20). Searches only read, so retries are safe apart from the per-query charge. Connector 1.3.0 (19 October 2026, now the default) adds a title and `readOnlyHint: true` and `openWorldHint: true` to `tools/list`, per the connector versions page read on 1 November. No `idempotentHint`, and older pinned targets don't carry the annotations until updated (16 of 20, up from 12 when annotations were unconfirmed). Only `query` is required, and since the default moved from 1.1.0 to 1.3.0 a target created without a version gets the filters. A first call still needs a gateway, a target, a service role and inbound auth. Any MCP client calls it, and set-up runs through AWS SDKs in many languages (12 of 15, up from 10).", "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": 75, "b": 85 } }, { "by": 5, "category": "payments", "leads": "agentcore-web-search", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 on the Gateway or the tool. AgentCore payments is a separate component for an agent paying third parties (0). Per-query price published without a login, $7.00 per 1,000, with a worked example that adds Gateway invocations at $0.005 per 1,000 (20). No Web Search allowance, but new AWS accounts get up to $200 in Free Tier credits and the Free Tier FAQ says most new customers need no payment method, so half, as on the other AWS listings (10). A person signs up in a browser and sets up a gateway, a target and IAM (0).", "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": 30, "b": 25 } } ], "facts": [ { "a": "MCP server", "b": "HTTP API", "name": "Kind" }, { "a": "Amazon Web Services", "b": "Perplexity", "name": "Vendor" }, { "a": "https://{gateway-id}.gateway.bedrock-agentcore.{region}.amazonaws.com/mcp", "b": "https://api.perplexity.ai/mcp", "name": "Hosted endpoint" }, { "a": "Streamable HTTP", "b": "Streamable HTTP, stdio", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth or key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "$7 per 1,000 requests", "b": "$1 per 1,000 requests", "name": "Price for web search" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the AWS Customer Agreement and Service Terms, with an acceptable-use section on the tool's documentation page", "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": "1", "b": "4", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "not listed", "b": "ai.perplexity/mcp-server", "name": "MCP registry" }, { "a": "2026-10-19", "b": "2026-10-23", "name": "Last release" }, { "a": "2026-10-01", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "2026-05-18", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "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": "not found in the text", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "3.3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Web Search Tool on Amazon Bedrock AgentCore scores 75.2 (BB) on agent readiness against Perplexity Search API's 70.2 (BB), and leads in 4 of 7 scored categories. Perplexity Search API leads on schema \u0026 documentation and agent ergonomics.", "question": "Which is better for AI agents, Web Search Tool on Amazon Bedrock AgentCore or Perplexity Search API?" }, { "answer": "Perplexity Search API, at $1 per 1,000 requests against $7 per 1,000 requests for Web Search Tool on Amazon Bedrock AgentCore. These are the vendors' published prices for the job.", "question": "Which is cheaper for web search, Web Search Tool on Amazon Bedrock AgentCore or Perplexity Search API?" }, { "answer": "Both take an API key or an OAuth sign-in.", "question": "Do Web Search Tool on Amazon Bedrock AgentCore and Perplexity Search API need an API key?" }, { "answer": "Yes. Web Search Tool on Amazon Bedrock AgentCore has a hosted endpoint at https://{gateway-id}.gateway.bedrock-agentcore.{region}.amazonaws.com/mcp and Perplexity Search API at https://api.perplexity.ai/mcp.", "question": "Can an agent call Web Search Tool on Amazon Bedrock AgentCore and Perplexity Search API without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 90 against 80", "Security \u0026 auth, 85 against 56", "Payments \u0026 pricing, 30 against 25", "Transparency \u0026 trust, 77 against 66" ], "also": [ "Free to start without a card" ], "goodFor": "A team already on AWS that wants agents to search the web through a governed MCP gateway, with owner-set domain lists, IAM or OAuth control and queries kept inside AWS.", "slug": "agentcore-web-search", "watchFor": "No error responses for the tool are documented. The only response example has `isError` false" }, { "aheadOn": [ "Schema \u0026 documentation, 89 against 78", "Agent ergonomics, 85 against 75" ], "also": [ "Cheaper for web search, $1 against $7 per 1,000 requests", "Runs on your own machine" ], "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": { "agentcore-web-search": [ { "causes": [ "product" ], "date": "2026-11-01", "delta": 0.9, "from": 74.3, "fromGrade": "BB", "to": 75.2, "toGrade": "BB" } ], "perplexity-search-api": null }, "job": { "capability": "web.search", "name": "Web 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-bing-grounding.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Grounding with Bing Search", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-bing-grounding" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-brave-search-mcp.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Brave Search API + MCP", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-brave-search-mcp" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-cloudflare-web-search.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Cloudflare Web Search API", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-cloudflare-web-search" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-deepseek-search-api.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs DeepSeek Search and Fetch API", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-deepseek-search-api" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-exa-mcp.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Exa API + MCP", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-exa-mcp" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-firecrawl-mcp.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Firecrawl MCP", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-firecrawl-mcp" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-grep-ai.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Grep AI", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-grep-ai" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-kagi-search.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Kagi Search API", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-kagi-search" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-linkup.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Linkup", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-linkup" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-mojeek.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Mojeek Web Search API", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-mojeek" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-newscatcher.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs NewsCatcher", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-newscatcher" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-parallel-search-api.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Parallel Search and Task APIs", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-parallel-search-api" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-searchapi-io.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs SearchAPI.io", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-searchapi-io" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-serpapi.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs SerpApi", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-serpapi" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-serper.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Serper", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-serper" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-serphouse.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs SERPHouse", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-serphouse" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-serpkite.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs SerpKite", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-serpkite" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-specstream.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs SpecStream", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-specstream" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-tavily-mcp.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Tavily API + MCP", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-tavily-mcp" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-tinyfish-search.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs TinyFish Search", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-tinyfish-search" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-valyu.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Valyu", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-valyu" }, { "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-you-com-api.json", "title": "Web Search Tool on Amazon Bedrock AgentCore vs You.com APIs", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-you-com-api" }, { "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-perplexity-search-api.json", "title": "Arcmira vs Perplexity Search API", "url": "https://www.anchorterminal.com/compare/arcmira-vs-perplexity-search-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": [ { "agentcore-web-search": 90, "by": 10, "edge": "agentcore-web-search", "key": "reliability", "name": "Reliability", "perplexity-search-api": 80, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "agentcore-web-search": 78, "by": 11, "edge": "perplexity-search-api", "key": "schema", "name": "Schema \u0026 documentation", "perplexity-search-api": 89, "weight": 13 }, { "agentcore-web-search": 75, "by": 10, "edge": "perplexity-search-api", "key": "ergonomics", "name": "Agent ergonomics", "perplexity-search-api": 85, "weight": 13 }, { "agentcore-web-search": 85, "by": 29, "edge": "agentcore-web-search", "key": "security", "name": "Security \u0026 auth", "perplexity-search-api": 56, "weight": 14 }, { "agentcore-web-search": 30, "by": 5, "edge": "agentcore-web-search", "key": "payments", "name": "Payments \u0026 pricing", "perplexity-search-api": 25, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "agentcore-web-search": 80, "by": 2, "edge": "perplexity-search-api", "key": "maintenance", "name": "Maintenance \u0026 community", "perplexity-search-api": 82, "weight": 7 }, { "agentcore-web-search": 77, "by": 11, "edge": "agentcore-web-search", "key": "transparency", "name": "Transparency \u0026 trust", "perplexity-search-api": 66, "weight": 7 } ], "summary": "Web Search Tool on Amazon Bedrock AgentCore scores 75.2 (BB) on agent readiness against Perplexity Search API's 70.2 (BB), and leads in 4 of 7 scored categories. Perplexity Search API leads on schema \u0026 documentation and agent ergonomics. Both do web search. Perplexity Search API is cheaper for web search, $1 against $7 per 1,000 requests.", "tasks": null, "tutorials": [], "verdicts": { "agentcore-web-search": "One compact MCP tool returns ranked snippets with URLs, titles and published dates from an Amazon-operated index, with domain and date filters and a read-only annotation on the default connector, at $7 per 1,000 queries. A first call needs an AWS account, a Gateway with inbound auth, a target and a service role, and tool errors are not documented.", "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/agentcore-web-search-vs-perplexity-search-api", "json": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-perplexity-search-api.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-perplexity-search-api.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-perplexity-search-api.min.md" }, "markdown": "Web Search Tool on Amazon Bedrock AgentCore scores 75.2 (BB) on agent readiness against Perplexity Search API's 70.2 (BB), and leads in 4 of 7 scored categories. Perplexity Search API leads on schema \u0026 documentation and agent ergonomics. Both do web search. Perplexity Search API is cheaper for web search, $1 against $7 per 1,000 requests.\n\n- Web Search Tool on Amazon Bedrock AgentCore: grade BB, 75.2/100, rank #70 of 1510. Markdown https://www.anchorterminal.com/tools/agentcore-web-search.md · JSON https://www.anchorterminal.com/api/v1/tools/agentcore-web-search.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### Web Search Tool on Amazon Bedrock AgentCore (BB)\n\nGood for: A team already on AWS that wants agents to search the web through a governed MCP gateway, with owner-set domain lists, IAM or OAuth control and queries kept inside AWS.\n\nAhead on:\n- Reliability, 90 against 80\n- Security \u0026 auth, 85 against 56\n- Payments \u0026 pricing, 30 against 25\n- Transparency \u0026 trust, 77 against 66\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: No error responses for the tool are documented. The only response example has `isError` false\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- Schema \u0026 documentation, 89 against 78\n- Agent ergonomics, 85 against 75\n\nAlso in its favour:\n- Cheaper for web search, $1 against $7 per 1,000 requests\n- Runs on your own machine\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### Security \u0026 auth: Web Search Tool on Amazon Bedrock AgentCore +29\n\n- Web Search Tool on Amazon Bedrock AgentCore (85): Gateway inbound auth is OAuth JWT from the owner's identity provider with allowed scopes advertised in the 401 challenge, or IAM SigV4 scoped to one gateway ARN, and the agent never holds a search credential (30). The tool only reads. The owner's target-level include and exclude lists cannot be relaxed by the agent, the service role's `InvokeWebSearch` names one service-owned ARN, and Cedar policies on the gateway can forbid the tool per caller. A no-authorisation gateway mode exists, with AWS's warning against production use (17 of 20). Results are third-party page text and the Web Search pages give no guidance on treating them as untrusted. Gateway guardrail policies can screen inputs for prompt attacks and suppress outputs, documented in general and not for this tool (7 of 15). CloudWatch metrics by method and tool name, and CloudTrail data events for `InvokeGateway` when the owner turns them on, at extra cost (13 of 15). A vulnerability disclosure programme on HackerOne, a security.txt that expires on 16 October 2027 (re-read on 1 November), and SOC and ISO 27001 among the programmes the AgentCore FAQ lists. No paid bounty found, so 2 held back as on every AWS listing (18 of 20).\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### Schema \u0026 documentation: Perplexity Search API +11\n\n- Web Search Tool on Amazon Bedrock AgentCore (78): The tool's `inputSchema` is published in full as JSON Schema, with `query` required, and the Gateway control plane is in AWS's service models (25). The developer guide has an llms.txt of 1,024 lines on 1 November and serves every page as Markdown (10). The page explains purpose, use cases, the two filter layers and how they compose, but says nothing on when another tool fits better (12 of 20). Types are given, but the 200-character limit on `query`, the 1 to 25 range of `maxResults` and the ISO-8601 date format sit in descriptions, with no `maxLength`, `minimum`, `maximum` or `format` (9 of 15). Python, AWS CLI and AgentCore CLI set-up examples and one response example. No error responses for the tool are documented, and the June release note links to a page that now redirects to the guide's front page (7 of 15). Semver connector versions with release dates (1.3.0 on 19 October 2026), a lifecycle table, monthly release notes and dated What's New posts (15).\n- Perplexity Search API (89): OpenAPI 3.1.0 at docs.perplexity.ai/openapi.json describes `POST /search` with typed request and response schemas, listed in llms.txt (25). llms.txt indexes every page, each with a Markdown twin (10). The overview says what a result holds, that snippets can be empty, when to use the Search API instead of the Agent API, and that it takes queries not URLs and does not re-fetch pages (19 of 20). `search_type` is an enum, `max_results`, `max_tokens` and `max_tokens_per_page` carry minimum and maximum, country and language codes carry lengths, and `query` is a string or an array. The recency filter is an enum in the docs, and date filters are `MM/DD/YYYY` strings (14 of 15). Python, TypeScript and cURL examples with a recorded response. The spec documents only 200 and 422 for `/search`, and status codes are listed on the SDK error-handling page and the rate-limit page rather than for Search (11 of 15). A public changelog with several entries a month, dated by month only, and an unversioned `/search` path (10 of 15). 25 + 10 + 19 + 14 + 11 + 10 = 89.\n\n### Transparency \u0026 trust: Web Search Tool on Amazon Bedrock AgentCore +11\n\n- Web Search Tool on Amazon Bedrock AgentCore (77): Closed service under the AWS Customer Agreement and Service Terms, updated 30 October 2026, with an acceptable-use section on the docs page (15 of 30). The docs say queries are served inside AWS and not sent to a third-party engine, the Gateway data protection notes say data is encrypted with a service key or a customer managed key, and section 50.3 of the Service Terms does not list AgentCore for content use. No retention period for queries was found (15 of 30). The connector versions page sets out stages from available to deprecated and retired and promises a migration guide for a major version, without a notice period (12 of 20). A sub-processor list updated 30 October 2026 and a per-Region availability list, and the August release note says queries stay in their Region (18 of 20).\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### Reliability: Web Search Tool on Amazon Bedrock AgentCore +10\n\n- Web Search Tool on Amazon Bedrock AgentCore (90): Graded on the hosted lines, for the Gateway endpoint and the connector agents call. AWS Health Dashboard with per-service, per-Region history (20). The dashboard's history file, re-read on 1 November 2026, names AgentCore in one event in the 90 days from 3 August, 2 hours 40 minutes of packet loss in one zone of eu-south-2 on 4 October 2026, marked informational and in a Region where Web Search is not sold. The us-west-2 events of 3 September and 30 October (API Gateway HTTP API) don't name AgentCore. Read as clean, as on the Memory listing (30). Quotas published and re-read on 1 November, 10 Web Search requests a second and 200 tool calls a second per gateway and per account (15). Owner-set gateway rate limits return an error body with `retryAfter` in seconds and searches have no side effects, but the response to the service's own Web Search quota is not documented (10 of 15). The AgentCore FAQ says the Amazon Bedrock SLA applies, but that SLA, last updated 4 October 2023, does not name AgentCore (5 of 10, as on the Code Interpreter listing). Generally available since 16 June 2026 (10).\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### Agent ergonomics: Perplexity Search API +10\n\n- Web Search Tool on Amazon Bedrock AgentCore (75): One tool with a compact schema, and results are snippets AWS says are extracted for model context. Each result comes as a JSON string in a text block and again as `structuredContent` (22 of 25). `maxResults` 1 to 25, per-request domain include and exclude lists and published-date bounds from 1.2.0. No pagination, offset, country or language controls (15 of 20). JWT failures return 401 or 403 with a `WWW-Authenticate` header naming the scopes, and throttling returns `retryAfter`, but no error codes for the tool itself are documented (10 of 20). Searches only read, so retries are safe apart from the per-query charge. Connector 1.3.0 (19 October 2026, now the default) adds a title and `readOnlyHint: true` and `openWorldHint: true` to `tools/list`, per the connector versions page read on 1 November. No `idempotentHint`, and older pinned targets don't carry the annotations until updated (16 of 20, up from 12 when annotations were unconfirmed). Only `query` is required, and since the default moved from 1.1.0 to 1.3.0 a target created without a version gets the filters. A first call still needs a gateway, a target, a service role and inbound auth. Any MCP client calls it, and set-up runs through AWS SDKs in many languages (12 of 15, up from 10).\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### Payments \u0026 pricing: Web Search Tool on Amazon Bedrock AgentCore +5\n\n- Web Search Tool on Amazon Bedrock AgentCore (30): No x402, MPP or L402 on the Gateway or the tool. AgentCore payments is a separate component for an agent paying third parties (0). Per-query price published without a login, $7.00 per 1,000, with a worked example that adds Gateway invocations at $0.005 per 1,000 (20). No Web Search allowance, but new AWS accounts get up to $200 in Free Tier credits and the Free Tier FAQ says most new customers need no payment method, so half, as on the other AWS listings (10). A person signs up in a browser and sets up a gateway, a target and IAM (0).\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## Score by category\n\n| Category | Weight | Web Search Tool on Amazon Bedrock AgentCore | Perplexity Search API | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 90 | 80 | Web Search Tool on Amazon Bedrock AgentCore +10 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 78 | 89 | Perplexity Search API +11 |\n| Agent ergonomics | 13% (16.2 this run) | 75 | 85 | Perplexity Search API +10 |\n| Security \u0026 auth | 14% (17.5 this run) | 85 | 56 | Web Search Tool on Amazon Bedrock AgentCore +29 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 25 | Web Search Tool on Amazon Bedrock AgentCore +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 82 | Perplexity Search API +2 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 77 | 66 | Web Search Tool on Amazon Bedrock AgentCore +11 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **75.2 · BB** | **70.2 · BB** | |\n\n## Facts side by side\n\n| Fact | Web Search Tool on Amazon Bedrock AgentCore | Perplexity Search API |\n| --- | --- | --- |\n| Kind | MCP server | HTTP API |\n| Vendor | Amazon Web Services | Perplexity |\n| Hosted endpoint | `https://{gateway-id}.gateway.bedrock-agentcore.{region}.amazonaws.com/mcp` | `https://api.perplexity.ai/mcp` |\n| Transports | Streamable HTTP | Streamable HTTP, stdio |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Pay per use | Pay per use |\n| Price for web search | $7 per 1,000 requests | $1 per 1,000 requests |\n| x402 | no | no |\n| Licence | Proprietary service under the AWS Customer Agreement and Service Terms, with an acceptable-use section on the tool's documentation page | Proprietary service under the Perplexity API Terms of Service. The MCP server is MIT and the official SDKs Apache-2.0 |\n| Tools exposed | 1 | 4 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | not listed | `ai.perplexity/mcp-server` |\n| Last release | 2026-10-19 | 2026-10-23 |\n| Terms last updated | 2026-10-01 | couldn't be read |\n| Privacy policy last updated | 2026-05-18 | couldn't be read |\n| Customer content may train models | yes, with an opt-out | 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 | not found in the text | couldn't be read |\n| Agent reviews | 3.3/5 (4) | none |\n\n## How the scores have moved\n\n### Web Search Tool on Amazon Bedrock AgentCore\n\n- +0.9 on 1 November 2026: product\n\n### Perplexity Search API\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Web Search Tool on Amazon Bedrock AgentCore.** One compact MCP tool returns ranked snippets with URLs, titles and published dates from an Amazon-operated index, with domain and date filters and a read-only annotation on the default connector, at $7 per 1,000 queries. A first call needs an AWS account, a Gateway with inbound auth, a target and a service role, and tool errors are not documented.\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### Web Search Tool on Amazon Bedrock AgentCore\n\n1. Call `tools/list` on the gateway and take the tool's name from it. AWS's call examples name gateway tools by target and tool\n2. Keep `query` to 200 characters and `maxResults` between 1 and 25 (default 10). The published schema states these limits only in descriptions\n3. Check the target's connector version before sending `filters`. Version 1.1.0 exposes only `query` and `maxResults`; 1.2.0 and the default 1.3.0 take filters\n4. Keep each result's URL and title with any answer built from it. AWS's acceptable-use terms require shown citations and bar storing results in bulk\n5. On a throttled request, wait the `retryAfter` seconds in the error body. The default quota is 10 Web Search requests a second, adjustable\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, Web Search Tool on Amazon Bedrock AgentCore or Perplexity Search API?\n\nWeb Search Tool on Amazon Bedrock AgentCore scores 75.2 (BB) on agent readiness against Perplexity Search API's 70.2 (BB), and leads in 4 of 7 scored categories. Perplexity Search API leads on schema \u0026 documentation and agent ergonomics.\n\n### Which is cheaper for web search, Web Search Tool on Amazon Bedrock AgentCore or Perplexity Search API?\n\nPerplexity Search API, at $1 per 1,000 requests against $7 per 1,000 requests for Web Search Tool on Amazon Bedrock AgentCore. These are the vendors' published prices for the job.\n\n### Do Web Search Tool on Amazon Bedrock AgentCore 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 Web Search Tool on Amazon Bedrock AgentCore and Perplexity Search API without installing anything?\n\nYes. Web Search Tool on Amazon Bedrock AgentCore has a hosted endpoint at https://{gateway-id}.gateway.bedrock-agentcore.{region}.amazonaws.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/agentcore-web-search-vs-perplexity-search-api.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agentcore-web-search-vs-perplexity-search-api.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"agentcore-web-search\", \"b\": \"perplexity-search-api\"}`. From a terminal: `anchor compare agentcore-web-search perplexity-search-api`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agentcore-web-search.json and https://www.anchorterminal.com/api/v1/tools/perplexity-search-api.json\n\n## Other comparisons with Web Search Tool on Amazon Bedrock AgentCore 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 Grounding with Bing Search](https://www.anchorterminal.com/compare/agentcore-web-search-vs-bing-grounding.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Brave Search API + MCP](https://www.anchorterminal.com/compare/agentcore-web-search-vs-brave-search-mcp.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Cloudflare Web Search API](https://www.anchorterminal.com/compare/agentcore-web-search-vs-cloudflare-web-search.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs DeepSeek Search and Fetch API](https://www.anchorterminal.com/compare/agentcore-web-search-vs-deepseek-search-api.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Exa API + MCP](https://www.anchorterminal.com/compare/agentcore-web-search-vs-exa-mcp.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Firecrawl MCP](https://www.anchorterminal.com/compare/agentcore-web-search-vs-firecrawl-mcp.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Grep AI](https://www.anchorterminal.com/compare/agentcore-web-search-vs-grep-ai.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Kagi Search API](https://www.anchorterminal.com/compare/agentcore-web-search-vs-kagi-search.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Linkup](https://www.anchorterminal.com/compare/agentcore-web-search-vs-linkup.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Mojeek Web Search API](https://www.anchorterminal.com/compare/agentcore-web-search-vs-mojeek.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs NewsCatcher](https://www.anchorterminal.com/compare/agentcore-web-search-vs-newscatcher.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/agentcore-web-search-vs-parallel-search-api.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs SearchAPI.io](https://www.anchorterminal.com/compare/agentcore-web-search-vs-searchapi-io.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs SerpApi](https://www.anchorterminal.com/compare/agentcore-web-search-vs-serpapi.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Serper](https://www.anchorterminal.com/compare/agentcore-web-search-vs-serper.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs SERPHouse](https://www.anchorterminal.com/compare/agentcore-web-search-vs-serphouse.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs SerpKite](https://www.anchorterminal.com/compare/agentcore-web-search-vs-serpkite.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs SpecStream](https://www.anchorterminal.com/compare/agentcore-web-search-vs-specstream.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Tavily API + MCP](https://www.anchorterminal.com/compare/agentcore-web-search-vs-tavily-mcp.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs TinyFish Search](https://www.anchorterminal.com/compare/agentcore-web-search-vs-tinyfish-search.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs Valyu](https://www.anchorterminal.com/compare/agentcore-web-search-vs-valyu.md)\n- [Web Search Tool on Amazon Bedrock AgentCore vs You.com APIs](https://www.anchorterminal.com/compare/agentcore-web-search-vs-you-com-api.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 Perplexity Search API](https://www.anchorterminal.com/compare/arcmira-vs-perplexity-search-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": "Web Search Tool on Amazon Bedrock AgentCore vs Perplexity Search API", "url": "" } ], "description": "Web Search Tool on Amazon Bedrock AgentCore scores 75.2 (BB) to Perplexity Search's 70.2 (BB) for web search. Perplexity Search is cheaper for web search, $1 against $7 per 1,000 requests. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Web Search Tool on Amazon Bedrock AgentCore BB 75.2", "Perplexity Search API BB 70.2", "scores" ], "h1": "Web Search Tool on Amazon Bedrock AgentCore vs Perplexity Search API", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/agentcore-web-search-vs-perplexity-search-api", "published": "2026-10-01", "section": "tools", "title": "Web Search Tool on Amazon Bedrock AgentCore vs Perplexity Search API", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/agentcore-web-search-vs-perplexity-search-api" }, "tokens": { "markdown": 7150, "slim": 4080 }, "version": 1 }