{ "data": { "similar": [ { "grade": "B", "json": "https://www.anchorterminal.com/tools/persona.json", "name": "Persona", "score": 69.5, "shared": [ "kyc.business", "kyc.documents", "kyc.screening" ], "slug": "persona" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/sumsub.json", "name": "Sumsub", "score": 68.5, "shared": [ "kyc.business", "kyc.documents", "kyc.screening" ], "slug": "sumsub" }, { "grade": "C", "json": "https://www.anchorterminal.com/tools/trulioo.json", "name": "Trulioo", "score": 58.2, "shared": [ "kyc.business", "kyc.documents", "kyc.screening" ], "slug": "trulioo" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/tavily-mcp.json", "name": "Tavily API + MCP", "score": 76.8, "shared": [ "search.answer", "search.research" ], "slug": "tavily-mcp" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/you-com-api.json", "name": "You.com APIs", "score": 76.5, "shared": [ "search.answer", "search.research" ], "slug": "you-com-api" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/parallel-search-api.json", "name": "Parallel Search and Task APIs", "score": 74, "shared": [ "search.answer", "search.research" ], "slug": "parallel-search-api" } ], "tool": { "slug": "grep-ai", "name": "Grep AI", "vendor": "Parcha Labs, Inc.", "vendorUrl": "https://grep.ai", "kind": "http-api", "category": "search", "summary": "Grep is a hosted platform from Parcha Labs for building and running research agents that return cited reports and structured output. Outside agents reach it through a REST API, a remote MCP server, an A2A endpoint and two SDKs.", "url": "https://www.anchorterminal.com/tools/grep-ai", "markdownUrl": "https://www.anchorterminal.com/tools/grep-ai.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/grep-ai.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/grep-ai.json", "repo": "https://github.com/Parcha-ai/grepai-skills", "license": "Proprietary service under Parcha Labs' terms of service. The grep-research-skills package on npm is MIT. The @parcha/agentrun and parcha-agentrun SDK packages state no licence in their registry metadata", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.grep.ai/api/v2/runs", "packages": [ { "registry": "npm", "name": "@parcha/agentrun" }, { "registry": "pypi", "name": "parcha-agentrun" }, { "registry": "npm", "name": "grep-research-skills" } ], "auth": "mixed", "authNotes": "A Bearer credential on every call except the public agent list and publicly shared runs. Self-serve API keys (`parcha-` prefix) are created in the developer dashboard or at POST /api/v2/keys, and can be listed and revoked. The MCP server and delegated integrations take OAuth access tokens issued by Descope, with scopes research:read, research:write, billing:read, experts:read and experts:write. An agent with an AgentMail inbox can sign in through AgentID with an Ed25519 key and no human account. No partner or sales approval is documented for the self-serve plans.", "pricing": "freemium", "pricingNotes": "Credits, with a medium-effort task counted as 20. The Free Trial has 100 one-time credits and the pricing table marks it without API access. Pay As You Go tops up a wallet from $20, also marked without API access. Pro is $200 a month for 1,500 credits and Ultra $500 for 4,500, both with API access. Team plans go through sales. The page says $20 buys 200 credits and its Markdown twin says 100. Whether signup needs a card isn't stated (https://grep.ai/pricing, checked 2026-10-08).", "priceSummary": "$200 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "Not available. The changelog entry of 8 May 2026 announces x402 and MPP payments for API research, but GET and POST requests to https://api.grep.ai/mpp/v1/api returned 503 `gateway_disabled` on 8 October 2026, and the grep-research-skills README says the wallet path returns once the gateway is generally available (checked 2026-10-08).", "endpoints": [] }, "toolCount": 82, "popularity": { "githubStars": null, "npmWeekly": 334, "pypiWeekly": 52, "asOf": "2026-10-08" }, "docsUrl": "https://grep.ai/developers", "llmsTxt": "https://grep.ai/llms.txt", "openapi": "https://api.grep.ai/api/v2/openapi.json", "capabilities": [ "search.research", "search.answer", "kyc.business", "kyc.screening", "kyc.documents" ], "tags": [ "hosted", "freemium", "mcp", "oauth", "openapi", "llms-txt", "python", "typescript", "async-jobs", "webhooks", "status-page" ], "lastRelease": "2026-09-30", "graded": true, "anchor": { "graded": true, "score": 64.4, "grade": "B", "agentReady": false, "rank": 252, "ranked": true, "rankOf": 629, "categoryRank": 9, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 70, "maintenance": 74, "payments": 40, "reliability": 60, "schema": 80, "security": 65, "transparency": 59 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 60, "points": 12, "reason": "Graded on the hosted API and MCP server. status.grep.ai runs on incident.io with a 90-day history, but its only component is Website, with none for the API or the MCP server (15). One incident in the last 90 days, \"Grep.ai currently unavailable\" on 4 September 2026, resolved after 24 minutes, so minor (20). No rate limit numbers found in the docs or the OpenAPI document (0). 429 `rate_limited` carries `Retry-After`, and run creation takes an `Idempotency-Key` with documented replay rules (15). The FAQ mentions SLA guarantees for enterprise customers, and no SLA is published (0). API v2 and the MCP server carry no beta label. The SDKs are at 0.2.1 and PyPI classifies the Python one as Alpha (10)." }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 80, "points": 13, "reason": "Public OpenAPI document at api.grep.ai/api/v2/openapi.json with 126 operations and 145 schemas (25). llms.txt and a Markdown twin of each developer page (10). Most operations carry a description, and the `effort` field says what each tier returns and how long it takes. 19 operations for campaigns, loops and batch schedules have none, and the MCP server card gives each of its 82 tools one line, one of them a placeholder. The MCP input schemas need OAuth and weren't read (12). 58 enums, numeric bounds and `additionalProperties: false` on the run request (12). Curl examples and an 11-code error registry in the docs, but the OpenAPI document has no examples and documents only 200 and 422 responses (9). The path is versioned, v1 is marked deprecated and the changelog is dated, with no entry after 24 July 2026 (12)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 70, "points": 11.38, "reason": "The MCP server card lists 82 tools, 31 of them deprecated aliases, with no documented toolsets. Reports default to plain Markdown and large files come back as signed URLs, so some credit back (8). Cursor pagination with `limit` on runs, timelines and transactions, and server-side filters on the skill and tool lists (18). One error envelope with stable codes and a `request_id`, and 402 for credits kept apart from 429 for rate (20). `Idempotency-Key` with body-hash matching and a 24-hour replay window. The server card shows no readOnlyHint or destructiveHint annotations, and the live tool list wasn't read (12). Only `question` is required and `effort` defaults to low. TypeScript and Python SDKs exist, though one docs page still calls the release pending and names a PyPI package that returns 404 (12)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 65, "points": 11.38, "reason": "OAuth through Descope with five scopes, and API keys that can be created with a subset of scopes, listed and revoked through the API (30). Read scopes, `validate_only` and `dry_run` on agent changes, a per-run `max_cost_usd` and versioned restores. No confirmation step for deletes or for making a run public (14). Reports are built from untrusted web pages. The docs describe an SSRF-guarded fetch for context files, and no prompt-injection guidance for callers was found (3). Each run has a timeline of execution events, and billing transactions and usage are readable through the API (12). The footer and FAQ claim SOC 2 Type II with no report or trust page linked. security.txt returns 404, and no disclosure policy or bug bounty was found (6). Webhooks are signed with the API key itself." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 40, "points": 5, "reason": "No machine payment protocol on the live endpoints. The changelog of 8 May 2026 announces x402 and MPP, and the gateway answered 503 `gateway_disabled` on 8 October 2026 (0). Plan and credit prices are public, but only the medium tier's credit cost is published and the page and its Markdown twin disagree on credits per dollar (10). 100 free trial credits, and 500 for an owner's first agent through AgentID. The pricing page doesn't say whether a card is needed, and its table marks the trial without API access (15). AgentID sign-in is documented as needing no human account, but it depends on an AgentMail inbox and a browser step, and we didn't run it (15)." }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 74, "points": 6.48, "reason": "@parcha/agentrun 0.2.1 on npm and parcha-agentrun 0.2.1 on PyPI, both on 30 September 2026 (30). Three npm releases of the SDK since 21 September, grep-research-skills 0.2.0 on 4 August, and changelog entries on 11 and 24 July (20). Closed service with a public changelog whose newest entry is 24 July 2026, and support at support@parcha.ai. We didn't test whether support answers (8). Current SDKs in two languages, with docs that lag them. Not found in the official MCP registry (12). The skills repository runs a test workflow. The SDK repositories named in the package metadata asked for credentials, so their CI wasn't read (4)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 59, "points": 5.16, "note": "editorial 36, provenance 82", "reason": "Closed service with published terms, written as an order-form contract that still points to grep.parcha.ai. The SDK packages state no licence, and the skills package is MIT (12). Section 12 of the terms says AI providers retain nothing and customer data isn't used for training. Section 4.2 grants a perpetual licence to use customer data to improve the platform, and the privacy policy gives retention only as \"as long as needed\". No DPA found (12). v1 is marked deprecated, /research answers with a `deprecation: true` header and a successor link, and 31 MCP tools are labelled deprecated, all without dates or a written policy (8). The privacy policy names Google Analytics and PostHog and says data may be processed in any country. No subprocessor list found (4)." } ], "assessment": { "date": "2026-10-08", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "The MCP server card lists 82 tools, 31 of them deprecated aliases, with no documented toolsets. Reports default to plain Markdown and large files come back as signed URLs, so some credit back (8). Cursor pagination with `limit` on runs, timelines and transactions, and server-side filters on the skill and tool lists (18). One error envelope with stable codes and a `request_id`, and 402 for credits kept apart from 429 for rate (20). `Idempotency-Key` with body-hash matching and a 24-hour replay window. The server card shows no readOnlyHint or destructiveHint annotations, and the live tool list wasn't read (12). Only `question` is required and `effort` defaults to low. TypeScript and Python SDKs exist, though one docs page still calls the release pending and names a PyPI package that returns 404 (12).", "maintenance": "@parcha/agentrun 0.2.1 on npm and parcha-agentrun 0.2.1 on PyPI, both on 30 September 2026 (30). Three npm releases of the SDK since 21 September, grep-research-skills 0.2.0 on 4 August, and changelog entries on 11 and 24 July (20). Closed service with a public changelog whose newest entry is 24 July 2026, and support at support@parcha.ai. We didn't test whether support answers (8). Current SDKs in two languages, with docs that lag them. Not found in the official MCP registry (12). The skills repository runs a test workflow. The SDK repositories named in the package metadata asked for credentials, so their CI wasn't read (4).", "payments": "No machine payment protocol on the live endpoints. The changelog of 8 May 2026 announces x402 and MPP, and the gateway answered 503 `gateway_disabled` on 8 October 2026 (0). Plan and credit prices are public, but only the medium tier's credit cost is published and the page and its Markdown twin disagree on credits per dollar (10). 100 free trial credits, and 500 for an owner's first agent through AgentID. The pricing page doesn't say whether a card is needed, and its table marks the trial without API access (15). AgentID sign-in is documented as needing no human account, but it depends on an AgentMail inbox and a browser step, and we didn't run it (15).", "reliability": "Graded on the hosted API and MCP server. status.grep.ai runs on incident.io with a 90-day history, but its only component is Website, with none for the API or the MCP server (15). One incident in the last 90 days, \"Grep.ai currently unavailable\" on 4 September 2026, resolved after 24 minutes, so minor (20). No rate limit numbers found in the docs or the OpenAPI document (0). 429 `rate_limited` carries `Retry-After`, and run creation takes an `Idempotency-Key` with documented replay rules (15). The FAQ mentions SLA guarantees for enterprise customers, and no SLA is published (0). API v2 and the MCP server carry no beta label. The SDKs are at 0.2.1 and PyPI classifies the Python one as Alpha (10).", "schema": "Public OpenAPI document at api.grep.ai/api/v2/openapi.json with 126 operations and 145 schemas (25). llms.txt and a Markdown twin of each developer page (10). Most operations carry a description, and the `effort` field says what each tier returns and how long it takes. 19 operations for campaigns, loops and batch schedules have none, and the MCP server card gives each of its 82 tools one line, one of them a placeholder. The MCP input schemas need OAuth and weren't read (12). 58 enums, numeric bounds and `additionalProperties: false` on the run request (12). Curl examples and an 11-code error registry in the docs, but the OpenAPI document has no examples and documents only 200 and 422 responses (9). The path is versioned, v1 is marked deprecated and the changelog is dated, with no entry after 24 July 2026 (12).", "security": "OAuth through Descope with five scopes, and API keys that can be created with a subset of scopes, listed and revoked through the API (30). Read scopes, `validate_only` and `dry_run` on agent changes, a per-run `max_cost_usd` and versioned restores. No confirmation step for deletes or for making a run public (14). Reports are built from untrusted web pages. The docs describe an SSRF-guarded fetch for context files, and no prompt-injection guidance for callers was found (3). Each run has a timeline of execution events, and billing transactions and usage are readable through the API (12). The footer and FAQ claim SOC 2 Type II with no report or trust page linked. security.txt returns 404, and no disclosure policy or bug bounty was found (6). Webhooks are signed with the API key itself.", "transparency": "Closed service with published terms, written as an order-form contract that still points to grep.parcha.ai. The SDK packages state no licence, and the skills package is MIT (12). Section 12 of the terms says AI providers retain nothing and customer data isn't used for training. Section 4.2 grants a perpetual licence to use customer data to improve the platform, and the privacy policy gives retention only as \"as long as needed\". No DPA found (12). v1 is marked deprecated, /research answers with a `deprecation: true` header and a successor link, and 31 MCP tools are labelled deprecated, all without dates or a written policy (8). The privacy policy names Google Analytics and PostHog and says data may be processed in any country. No subprocessor list found (4)." }, "sources": [ { "what": "llms.txt", "url": "https://grep.ai/llms.txt", "seen": "2026-10-08" }, { "what": "OpenAPI document", "url": "https://api.grep.ai/api/v2/openapi.json", "seen": "2026-10-08" }, { "what": "developer docs", "url": "https://grep.ai/developers.md", "seen": "2026-10-08" }, { "what": "authentication", "url": "https://grep.ai/developers/api/auth.md", "seen": "2026-10-08" }, { "what": "errors", "url": "https://grep.ai/developers/api/errors.md", "seen": "2026-10-08" }, { "what": "idempotency", "url": "https://grep.ai/developers/api/idempotency.md", "seen": "2026-10-08" }, { "what": "pagination", "url": "https://grep.ai/developers/api/pagination.md", "seen": "2026-10-08" }, { "what": "webhooks", "url": "https://grep.ai/developers/api/webhooks.md", "seen": "2026-10-08" }, { "what": "AgentID sign-in", "url": "https://grep.ai/developers/api/agentid.md", "seen": "2026-10-08" }, { "what": "MCP server docs", "url": "https://grep.ai/developers/mcp.md", "seen": "2026-10-08" }, { "what": "MCP server card", "url": "https://grep.ai/.well-known/mcp/server-card.json", "seen": "2026-10-08" }, { "what": "OAuth protected-resource metadata", "url": "https://api.grep.ai/.well-known/oauth-protected-resource/mcp", "seen": "2026-10-08" }, { "what": "A2A agent card", "url": "https://grep.ai/.well-known/agent-card.json", "seen": "2026-10-08" }, { "what": "SDK overview", "url": "https://grep.ai/developers/sdks.md", "seen": "2026-10-08" }, { "what": "SDK errors and retries", "url": "https://grep.ai/developers/sdks/errors.md", "seen": "2026-10-08" }, { "what": "agent onboarding guide", "url": "https://grep.ai/get-started.md", "seen": "2026-10-08" }, { "what": "pricing page", "url": "https://grep.ai/pricing", "seen": "2026-10-08" }, { "what": "pricing page, Markdown twin", "url": "https://grep.ai/pricing.md", "seen": "2026-10-08" }, { "what": "terms of service", "url": "https://grep.ai/terms", "seen": "2026-10-08" }, { "what": "privacy policy", "url": "https://grep.ai/privacy", "seen": "2026-10-08" }, { "what": "changelog", "url": "https://grep.ai/changelog", "seen": "2026-10-08" }, { "what": "FAQ", "url": "https://grep.ai/faq", "seen": "2026-10-08" }, { "what": "status page incidents", "url": "https://status.grep.ai/api/v2/incidents.json", "seen": "2026-10-08" }, { "what": "public agent list", "url": "https://api.grep.ai/api/v2/agents", "seen": "2026-10-08" }, { "what": "payment gateway probe", "url": "https://api.grep.ai/mpp/v1/api", "seen": "2026-10-08" }, { "what": "TypeScript SDK on npm", "url": "https://registry.npmjs.org/@parcha/agentrun", "seen": "2026-10-08" }, { "what": "skills package on npm", "url": "https://registry.npmjs.org/grep-research-skills", "seen": "2026-10-08" }, { "what": "Python SDK on PyPI", "url": "https://pypi.org/pypi/parcha-agentrun/json", "seen": "2026-10-08" }, { "what": "skills repository", "url": "https://github.com/Parcha-ai/grepai-skills", "seen": "2026-10-08" }, { "what": "MCP registry search", "url": "https://registry.modelcontextprotocol.io/v0/servers?search=parcha", "seen": "2026-10-08" }, { "what": "Y Combinator company page", "url": "https://www.ycombinator.com/companies/grep-ai", "seen": "2026-10-08" }, { "what": "domain registration", "url": "https://rdap.identitydigital.services/rdap/domain/grep.ai", "seen": "2026-10-08" }, { "what": "security.txt", "url": "https://grep.ai/.well-known/security.txt", "seen": "2026-10-08" } ], "openQuestions": [ "unchecked: the MCP tool input schemas and annotations, because tools/list needs an OAuth sign-in. The server card gives names and one-line descriptions only", "unchecked: whether Free Trial, Pay As You Go or AgentID accounts can call the API or MCP server. The pricing table says API access is Pro and Ultra only, and no account was opened", "unchecked: whether signup needs a card", "unchecked: GitHub stars and issue activity, because the GitHub API refused us for its rate limit. The SDK repositories named in the package metadata asked for credentials", "unchecked: the SOC 2 Type II report, which the footer and FAQ claim without a link", "Credits per dollar on Pay As You Go. The pricing page says $20 for 200 credits and its Markdown twin says 100", "Free credits are given as 100 on the pricing page, 1,000 in the FAQ and 500 for AgentID sign-ins", "Judgement call. The changelog still carries the 8 May 2026 x402 and MPP announcement while the gateway is disabled. We took no deduction because the entry is dated history and the skills README states the gateway isn't generally available", "The scout wrote that the site doesn't name Parcha. The terms, privacy policy and footer name Parcha Labs, Inc.", "Category fit is weak. Grep is a hosted agent platform, and search.research covers only the part an outside agent calls for a cited report" ] }, "negative": 0, "verdict": "The public API has a 126-operation OpenAPI document, scoped OAuth and API keys, idempotency keys with documented replay rules and a per-run cost cap. No rate limit is published, the MCP server lists 82 tools, and the pricing page limits API access to the $200 a month Pro plan and above.", "bestFor": "Agents that hand off a long research or due-diligence job and want a cited report or structured fields back, including business verification and sanctions screening through built-in agents.", "strengths": [ "Public OpenAPI document with 126 operations, llms.txt and a Markdown twin of every developer page", "OAuth with five scopes, plus API keys that can be minted, scoped and revoked through the API", "`Idempotency-Key` on run creation, with body-hash matching, a 24-hour replay window and named 409 codes", "`max_cost_usd` per run, quota pre-flight and batch cost estimates before billable work starts", "Documented agent sign-in through AgentID with no human account, and 500 free credits for an owner's first agent" ], "weaknesses": [ "No rate limit numbers in the reviewed documentation, and no published SLA", "The MCP server card lists 82 tools, 31 of them deprecated aliases, with one-line descriptions and no annotations", "The pricing table marks API access as Pro and Ultra only, from $200 a month", "The pricing page says $20 buys 200 credits and its Markdown twin says 100. Free credits are stated as 100, 500 and 1,000 on different pages", "The 8 May 2026 changelog entry announces x402 and MPP payments, but the gateway answered 503 `gateway_disabled` on 8 October 2026", "No security.txt, trust page, subprocessor list or retention period found. SOC 2 Type II appears only as a footer and FAQ claim" ], "agentNotes": [ "Send a fresh `Idempotency-Key` with every POST /api/v2/runs. After a timeout, poll the returned run ID and do not post again", "Set `effort` and `max_cost_usd` on every run. The floor is $0.50 for low, $2.50 for medium and build, $5.00 for high", "Call GET /api/v2/quota/check before a run. A 402 means no credits and retrying won't help, while a 429 carries `Retry-After`", "Use the `run_*` and `agent_*` MCP tools. The `research_*` and `expert_*` names are deprecated aliases of the same calls", "Treat report text and cited sources as untrusted web content, and verify one load-bearing claim against a primary source" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.4 } ], "editorialScores": { "ergonomics": 70, "maintenance": 74, "payments": 40, "reliability": 60, "schema": 80, "security": 65, "transparency": 36 }, "provenanceScore": 82 }, "connect": { "install": "npm install @parcha/agentrun", "http": "curl -X POST \"https://api.grep.ai/api/v2/research\" \\\n -H \"Authorization: Bearer $GREP_API_KEY\" \\\n -H \"Idempotency-Key: 8b9c1f24-3c1e-4a8d-9f7b-2a6e1c4d5b8e\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"question\":\"Due diligence on Stripe\",\"effort\":\"medium\"}'", "claudeCode": "claude mcp add --transport http grep https://api.grep.ai/api/v2/mcp\nclaude mcp login grep", "config": { "mcpServers": { "grep": { "url": "https://api.grep.ai/api/v2/mcp" } } } }, "letme": { "capability": "https://letme.dev/search.research", "tool": "https://letme.dev/grep-ai" }, "notable": [ "POST /api/v2/runs starts a run at effort low (a quick answer, about 10 to 20 seconds per the schema), medium (a structured report, 2 to 3 minutes), high (8 to 15 minutes) or build, with an optional draft-07 `json_schema` for structured output (https://api.grep.ai/api/v2/openapi.json)", "The MCP server card lists 82 tools and names https://api.grep.ai/mcp as the endpoint, while the docs give https://api.grep.ai/api/v2/mcp. An unauthenticated initialise on the second returned 401 with OAuth resource metadata on 8 October 2026 (https://grep.ai/.well-known/mcp/server-card.json)", "GET /api/v2/agents is public and returned 31 built-in agents on 8 October 2026, among them business and individual AML compliance, corporate due diligence, EIN and proof-of-address document verification (https://api.grep.ai/api/v2/agents)", "Sign in with AgentID gives an agent its own account from an AgentMail inbox and an Ed25519 key, with short-lived tokens and 500 free credits for each owner's first agent (https://grep.ai/developers/api/agentid)", "The x402 and MPP gateway announced in the changelog on 8 May 2026 is switched off. GET https://api.grep.ai/mpp/v1/api returned 503 `gateway_disabled` on 8 October 2026, and the skills package README says the wallet path returns once the gateway is generally available (https://grep.ai/changelog)", "Grep is the product of Parcha Labs, Inc., a Delaware corporation. API keys carry the prefix `parcha-`, and the company launched on Y Combinator's Fall 2026 page on 5 October 2026 with a team of 6 (https://www.ycombinator.com/companies/grep-ai)", "Webhook deliveries are signed with HMAC-SHA256 keyed by the API key itself, retried up to 3 times within a 30-second budget (https://grep.ai/developers/api/webhooks)" ], "area": "web-data", "details": [ { "label": "API", "value": "REST API v2 at https://api.grep.ai/api/v2, 126 operations in the OpenAPI document. Runs, agents, skills, attachments, batches, loops, campaigns, keys, quota and billing. /research is marked deprecated in favour of /runs" }, { "label": "MCP server", "value": "Remote, streamable HTTP, OAuth through Descope. 82 tools in the server card, 31 of them deprecated aliases. Docs give https://api.grep.ai/api/v2/mcp and the card gives https://api.grep.ai/mcp" }, { "label": "A2A", "value": "Agent card at https://grep.ai/.well-known/agent-card.json, JSON-RPC at https://api.grep.ai/api/v2/a2a with SendMessage, GetTask, streaming and CancelTask" }, { "label": "Answer or report", "value": "Markdown report with inline citations, optional `structured_output` against a caller's JSON Schema, a timeline of execution events and generated files" }, { "label": "Effort tiers", "value": "low, medium, high and build. Default low. The pricing page counts a medium task as 20 credits" }, { "label": "Credentials", "value": "API keys (`parcha-` prefix) or OAuth access tokens. Scopes research:read, research:write, billing:read, experts:read, experts:write. Keys can be created, listed and revoked at /api/v2/keys" }, { "label": "Rate limits", "value": "No numbers found. 429 `rate_limited` carries `Retry-After`" }, { "label": "Idempotency", "value": "`Idempotency-Key` on run creation. Replay for 24 hours after a job ends and 1 hour while pending. Reuse with a different body returns 409" }, { "label": "Errors", "value": "One envelope with `code`, `message`, `details` and `request_id`. 11 documented codes, with 402 `insufficient_credits` kept apart from 429 `rate_limited`" }, { "label": "Webhooks", "value": "`webhook_url` on a run, one POST at completion or failure, `X-Signature-SHA256` keyed by the API key, up to 3 attempts in 30 seconds" }, { "label": "SDKs", "value": "TypeScript @parcha/agentrun 0.2.1 and Python parcha-agentrun 0.2.1, both published 30 September 2026. PyPI classifies the Python package as Alpha. Neither retries requests automatically" }, { "label": "Free tier", "value": "100 one-time credits on the Free Trial per the pricing page, without API access. 500 credits for an owner's first agent through AgentID" }, { "label": "Status", "value": "status.grep.ai on incident.io, one component (Website), 90-day history. One incident in the last 90 days, 24 minutes on 4 September 2026" } ], "unitPrices": [ { "item": "Pro plan, 1,500 credits a month, API access", "unit": "month", "usd": 200, "note": "$167 a month billed annually" }, { "item": "Ultra plan, 4,500 credits a month", "unit": "month", "usd": 500, "note": "$417 a month billed annually" }, { "item": "Pay As You Go credit", "unit": "credit", "usd": 0.1, "note": "$20 for 200 credits on the pricing page. Its Markdown twin says 100 credits, which is $0.20. No API access on this plan per the table" } ], "provenance": { "legalEntity": "Parcha Labs, Inc.", "domain": "grep.ai", "domainRegistered": "2018-04-20", "domainNote": "Registered in 2018 and transferred on 2025-10-19, so the registration date predates the company's use of it.", "endpointOnVendorDomain": true, "terms": "https://grep.ai/terms", "privacy": "https://grep.ai/privacy", "statusPage": "https://status.grep.ai", "changelog": "https://grep.ai/changelog", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms of service, last updated 20 March 2026, are a contract with Parcha Labs, Inc., a Delaware corporation, governed by California law.", "The privacy policy, last updated 5 October 2026, names Parcha Labs, Inc. and the websites www.parcha.ai and grep.parcha.ai.", "The API, the MCP server and the A2A endpoint answer on api.grep.ai. OAuth tokens come from Descope at api.descope.com.", "grep.ai/.well-known/security.txt and api.grep.ai/.well-known/security.txt return 404. grep.ai/trust and grep.ai/security return 404.", "RDAP for grep.ai gives a registration date of 2018-04-20 and a transfer on 2025-10-19.", "The status page's support link is support@parcha.ai and its privacy link points to parcha.ai." ], "score": 82, "checks": [ { "check": "Legal entity named", "value": "Parcha Labs, Inc.", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "grep.ai, registered 2018-04-20 (8 years)", "points": 11, "max": 15, "state": "part" }, { "check": "Endpoint on the vendor's domain", "value": "api.grep.ai", "points": 15, "max": 15, "state": "ok" }, { "check": "Terms of service", "value": "read, states 5 of the 7 things a reader expects, and has 1 clause that costs points", "points": 6.3, "max": 10, "state": "part" }, { "check": "Privacy policy", "value": "read, states 8 of the 8 things a reader expects", "points": 10, "max": 10, "state": "ok" }, { "check": "Status page", "value": "status.grep.ai", "points": 10, "max": 10, "state": "ok" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" } ], "policies": [ { "kind": "terms", "url": "https://grep.ai/terms", "state": "read", "readAt": "2026-10-08", "statedDate": "2026-03-20", "words": 1550, "points": 6.3, "max": 10, "expected": [ { "key": "terms.date", "label": "Gives the date it was last updated", "found": true, "quote": "Effective date: March 20, 2026", "says": "Last updated 2026-03-20" }, { "key": "terms.law", "label": "Names the governing law or courts", "found": true, "quote": "This Agreement shall be governed by the laws of the State of California.", "says": "The law of the State of California" }, { "key": "terms.liability", "label": "States a limit on its liability", "found": true, "quote": "PARCHA’S AGGREGATE LIABILITY SHALL NOT EXCEED ONE HUNDRED DOLLARS ($100).", "says": "Capped at $100" }, { "key": "terms.termination", "label": "Says how the agreement or account can be ended", "found": true, "quote": "Parcha may terminate upon written notice if no Order Form is in effect, or immediately if Customer materially breaches this Agreement or fails to pay amounts due." }, { "key": "terms.changes", "label": "Says how changes to the terms are announced", "found": false }, { "key": "terms.use", "label": "Lists what users may not do", "found": true, "quote": "IF YOU DO NOT AGREE TO THESE TERMS, YOU MAY NOT ACCESS OR USE THE SERVICES." }, { "key": "terms.sla", "label": "Refers to a service level or uptime commitment", "found": false } ], "toKnow": [ { "key": "terms.automated", "label": "Restricts automated access", "found": true, "quote": "Use any robot, spider, or data scraping tool;", "costsPoints": true } ], "notes": [ { "date": "2026-10-08", "text": "Parcha's aggregate liability is capped at 100 US dollars.", "quote": "PARCHA’S AGGREGATE LIABILITY SHALL NOT EXCEED ONE HUNDRED DOLLARS ($100)." }, { "date": "2026-10-08", "text": "The customer grants a perpetual, irrevocable, transferable and sub-licensable licence to use Customer Data to run the services and to improve the platform.", "quote": "Customer hereby grants Parcha a fully paid-up, royalty-free, worldwide, transferable, sub-licensable, irrevocable and perpetual license to use Customer Data to provide the Services and to improve the Platform, and to use all feedback for any purpose." }, { "date": "2026-10-08", "text": "The terms say Parcha will not use Customer Data to train, fine-tune or improve machine learning or AI models.", "quote": "PARCHA LABS SHALL NOT USE CUSTOMER DATA FOR THE PURPOSE OF TRAINING, FINE-TUNING, OR IMPROVING MACHINE LEARNING OR ARTIFICIAL INTELLIGENCE MODELS." } ] }, { "kind": "privacy", "url": "https://grep.ai/privacy", "state": "read", "readAt": "2026-10-08", "statedDate": "2026-09-21", "words": 3267, "points": 10, "max": 10, "expected": [ { "key": "privacy.date", "label": "Gives the date it was last updated", "found": true, "quote": "Effective date: September 21, 2026", "says": "Last updated 2026-09-21" }, { "key": "privacy.collected", "label": "Says what personal data is collected", "found": true, "quote": "(the Company, we, or us) is providing this privacy policy (the Privacy Policy) to describe how we collect, use, and disclose personal information obtained through (1) our website at www.parcha.ai and www.grep.ai and any other websites operated by us that link to this Privacy Policy (collectively, the Website), and (2)…" }, { "key": "privacy.retention", "label": "Says how long data is kept", "found": true, "quote": "We retain personal information for as long as needed or permitted in light of the purpose(s) for which it was obtained and consistent with applicable law.", "says": "For as long as needed, with no period named" }, { "key": "privacy.processors", "label": "Says who else receives the data", "found": true, "quote": "When we process personal information on behalf of our enterprise customers, we act as a data processor (or service provider) under applicable law, and such processing is governed by our agreements with those customers." }, { "key": "privacy.sale", "label": "Says whether personal data is sold or shared for advertising", "found": true, "quote": "We do not sell or share the personal information of consumers we know to be under 16 years of age.", "says": "Says it does not sell personal data" }, { "key": "privacy.rights", "label": "Says what rights people have over their data", "found": true, "quote": "Withdrawing Consent: You have the right to withdraw your consent at any time by adjusting your browser settings to refuse cookies or by updating your preferences through our cookie banner." }, { "key": "privacy.contact", "label": "Gives a privacy contact", "found": true, "quote": "You may withdraw consent at any time by contacting us at [email protected].", "says": "Gives an email address, hidden from our reader by the page" }, { "key": "privacy.transfers", "label": "Says where data is transferred or stored", "found": true, "quote": "…adequate level of data protection, we rely on appropriate safeguards, such as the European Commission's Standard Contractual Clauses (and the UK Addendum thereto, as applicable), to lawfully transfer your data.", "says": "Relies on standard contractual clauses" } ], "toKnow": [ { "key": "privacy.sells", "label": "Says it sells personal data or shares it for advertising", "found": true, "quote": "This may constitute a “sale” or “sharing” of personal information under the CCPA/CPRA, even though no money changes hands." } ], "notes": [ { "date": "2026-10-08", "text": "Where the platform makes solely automated decisions with legal or similarly significant effects, the policy places responsibility for safeguards on the enterprise customer as data controller.", "quote": "our enterprise customers, as the data controllers, are responsible for ensuring that appropriate safeguards are in place, including the right to obtain human intervention, to express a point of view, and to contest the decision." } ] } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/grep-ai.json", "live": { "slug": "grep-ai", "probe": { "target": "https://api.grep.ai/api/v2/runs", "method": "get", "lastAt": "2026-10-08T18:20:31.107787042Z", "lastOk": true, "lastStatus": 401, "lastMs": 186, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 382, "p95ms24h": 533, "samples24h": 33, "samples30d": 33, "days": [ { "date": "2026-10-08", "probes": 33, "ok": 33 } ] }, "vendorStatus": { "page": "https://status.grep.ai", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-08T18:22:02.684990095Z" }, "versions": [ { "registry": "github", "name": "Parcha-ai/grepai-skills", "version": "v0.2.0", "released": "2026-08-04", "seenAt": "2026-10-08T16:15:07.589068505Z" }, { "registry": "npm", "name": "@parcha/agentrun", "version": "0.2.1", "seenAt": "2026-10-08T16:15:03.929041874Z" }, { "registry": "npm", "name": "grep-research-skills", "version": "0.2.0", "seenAt": "2026-10-08T16:15:07.371903924Z" }, { "registry": "pypi", "name": "parcha-agentrun", "version": "0.2.1", "released": "2026-09-30", "seenAt": "2026-10-08T16:15:07.178365237Z" } ], "githubStars": 2, "npmWeekly": 334, "pypiWeekly": 52, "securityTxt": { "url": "https://grep.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:56.474115574Z" }, "pages": [ { "url": "https://grep.ai/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:20:43.809396033Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "5f4c7902b1e3" }, { "url": "https://grep.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-08T18:20:46.272067131Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "a9ffcdfc713c" }, { "url": "https://grep.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:20:48.076387468Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "68d0ef896769" }, { "url": "https://grep.ai/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:20:50.381060662Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "5c21afb05a2d" } ], "updatedAt": "2026-10-08T18:22:02.684990095Z" } }, "verify": { "accepts": "a page on grep.ai or one of its subdomains, or the README of github.com/Parcha-ai/grepai-skills", "badgeUrl": "https://www.anchorterminal.com/badges/grep-ai.svg", "body": { "slug": "grep-ai", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/grep-ai", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/grep-ai\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/grep-ai.svg\" alt=\"Grep AI on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![Grep AI on Anchor Terminal](https://www.anchorterminal.com/badges/grep-ai.svg)](https://www.anchorterminal.com/tools/grep-ai)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/grep-ai\"\u003eGrep AI on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/grep-ai", "json": "https://www.anchorterminal.com/tools/grep-ai.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/grep-ai.md", "slim": "https://www.anchorterminal.com/tools/grep-ai.min.md" }, "markdown": "## Overview\n\n**Grade B · 64.4/100 · rank #252 of 629 · #9 in Web search APIs · not agent-ready · confidence medium**\n\n\n## Assessment\n\nThe public API has a 126-operation OpenAPI document, scoped OAuth and API keys, idempotency keys with documented replay rules and a per-run cost cap. No rate limit is published, the MCP server lists 82 tools, and the pricing page limits API access to the $200 a month Pro plan and above.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | Parcha Labs, Inc. (https://grep.ai) |\n| Kind | HTTP API |\n| Category | Web search APIs (https://www.anchorterminal.com/categories/search) |\n| Transport | HTTP, Streamable HTTP |\n| Endpoint | `https://api.grep.ai/api/v2/runs` |\n| Auth | OAuth or key · A Bearer credential on every call except the public agent list and publicly shared runs. Self-serve API keys (`parcha-` prefix) are created in the developer dashboard or at POST /api/v2/keys, and can be listed and revoked. The MCP server and delegated integrations take OAuth access tokens issued by Descope, with scopes research:read, research:write, billing:read, experts:read and experts:write. An agent with an AgentMail inbox can sign in through AgentID with an Ed25519 key and no human account. No partner or sales approval is documented for the self-serve plans. |\n| Pricing | Freemium ($200 / mo) · Credits, with a medium-effort task counted as 20. The Free Trial has 100 one-time credits and the pricing table marks it without API access. Pay As You Go tops up a wallet from $20, also marked without API access. Pro is $200 a month for 1,500 credits and Ultra $500 for 4,500, both with API access. Team plans go through sales. The page says $20 buys 200 credits and its Markdown twin says 100. Whether signup needs a card isn't stated (https://grep.ai/pricing, checked 2026-10-08). |\n| x402 | No · Not available. The changelog entry of 8 May 2026 announces x402 and MPP payments for API research, but GET and POST requests to https://api.grep.ai/mpp/v1/api returned 503 `gateway_disabled` on 8 October 2026, and the grep-research-skills README says the wallet path returns once the gateway is generally available (checked 2026-10-08). |\n| Licence | Proprietary service under Parcha Labs' terms of service. The grep-research-skills package on npm is MIT. The @parcha/agentrun and parcha-agentrun SDK packages state no licence in their registry metadata |\n| Tools exposed | 82 |\n| Packages | npm: `@parcha/agentrun`; pypi: `parcha-agentrun`; npm: `grep-research-skills` |\n| Source | https://github.com/Parcha-ai/grepai-skills |\n| Docs | https://grep.ai/developers |\n| llms.txt | https://grep.ai/llms.txt |\n| Last release | 2026-09-30 |\n| npm downloads / week | 334 |\n| PyPI downloads / week | 52 |\n| API | REST API v2 at https://api.grep.ai/api/v2, 126 operations in the OpenAPI document. Runs, agents, skills, attachments, batches, loops, campaigns, keys, quota and billing. /research is marked deprecated in favour of /runs |\n| MCP server | Remote, streamable HTTP, OAuth through Descope. 82 tools in the server card, 31 of them deprecated aliases. Docs give https://api.grep.ai/api/v2/mcp and the card gives https://api.grep.ai/mcp |\n| A2A | Agent card at https://grep.ai/.well-known/agent-card.json, JSON-RPC at https://api.grep.ai/api/v2/a2a with SendMessage, GetTask, streaming and CancelTask |\n| Answer or report | Markdown report with inline citations, optional `structured_output` against a caller's JSON Schema, a timeline of execution events and generated files |\n| Effort tiers | low, medium, high and build. Default low. The pricing page counts a medium task as 20 credits |\n| Credentials | API keys (`parcha-` prefix) or OAuth access tokens. Scopes research:read, research:write, billing:read, experts:read, experts:write. Keys can be created, listed and revoked at /api/v2/keys |\n| Rate limits | No numbers found. 429 `rate_limited` carries `Retry-After` |\n| Idempotency | `Idempotency-Key` on run creation. Replay for 24 hours after a job ends and 1 hour while pending. Reuse with a different body returns 409 |\n| Errors | One envelope with `code`, `message`, `details` and `request_id`. 11 documented codes, with 402 `insufficient_credits` kept apart from 429 `rate_limited` |\n| Webhooks | `webhook_url` on a run, one POST at completion or failure, `X-Signature-SHA256` keyed by the API key, up to 3 attempts in 30 seconds |\n| SDKs | TypeScript @parcha/agentrun 0.2.1 and Python parcha-agentrun 0.2.1, both published 30 September 2026. PyPI classifies the Python package as Alpha. Neither retries requests automatically |\n| Free tier | 100 one-time credits on the Free Trial per the pricing page, without API access. 500 credits for an owner's first agent through AgentID |\n| Status | status.grep.ai on incident.io, one component (Website), 90-day history. One incident in the last 90 days, 24 minutes on 4 September 2026 |\n| Capabilities | search.research, search.answer, kyc.business, kyc.screening, kyc.documents |\n| Tags | hosted, freemium, mcp, oauth, openapi, llms-txt, python, typescript, async-jobs, webhooks, status-page |\n| JSON | https://www.anchorterminal.com/api/v1/tools/grep-ai.json |\n\n## Score breakdown (methodology v0.4, October 2026 research run)\n\nAssessed 2026-10-08 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 60 | 12.0 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 80 | 13.0 |\n| Agent ergonomics | 13% | 16.2 | 70 | 11.4 |\n| Security \u0026 auth | 14% | 17.5 | 65 | 11.4 |\n| Payments \u0026 pricing | 10% | 12.5 | 40 | 5.0 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 74 | 6.5 |\n| Transparency \u0026 trust (editorial 36, provenance 82) | 7% | 8.8 | 59 | 5.2 |\n| Negative events | up to −15 | up to −15 | none recorded | 0 |\n| **Total** | | | | **64.4 → B** |\n\n### Why each score\n\n- Reliability 60: Graded on the hosted API and MCP server. status.grep.ai runs on incident.io with a 90-day history, but its only component is Website, with none for the API or the MCP server (15). One incident in the last 90 days, \"Grep.ai currently unavailable\" on 4 September 2026, resolved after 24 minutes, so minor (20). No rate limit numbers found in the docs or the OpenAPI document (0). 429 `rate_limited` carries `Retry-After`, and run creation takes an `Idempotency-Key` with documented replay rules (15). The FAQ mentions SLA guarantees for enterprise customers, and no SLA is published (0). API v2 and the MCP server carry no beta label. The SDKs are at 0.2.1 and PyPI classifies the Python one as Alpha (10).\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 80: Public OpenAPI document at api.grep.ai/api/v2/openapi.json with 126 operations and 145 schemas (25). llms.txt and a Markdown twin of each developer page (10). Most operations carry a description, and the `effort` field says what each tier returns and how long it takes. 19 operations for campaigns, loops and batch schedules have none, and the MCP server card gives each of its 82 tools one line, one of them a placeholder. The MCP input schemas need OAuth and weren't read (12). 58 enums, numeric bounds and `additionalProperties: false` on the run request (12). Curl examples and an 11-code error registry in the docs, but the OpenAPI document has no examples and documents only 200 and 422 responses (9). The path is versioned, v1 is marked deprecated and the changelog is dated, with no entry after 24 July 2026 (12).\n- Agent ergonomics 70: The MCP server card lists 82 tools, 31 of them deprecated aliases, with no documented toolsets. Reports default to plain Markdown and large files come back as signed URLs, so some credit back (8). Cursor pagination with `limit` on runs, timelines and transactions, and server-side filters on the skill and tool lists (18). One error envelope with stable codes and a `request_id`, and 402 for credits kept apart from 429 for rate (20). `Idempotency-Key` with body-hash matching and a 24-hour replay window. The server card shows no readOnlyHint or destructiveHint annotations, and the live tool list wasn't read (12). Only `question` is required and `effort` defaults to low. TypeScript and Python SDKs exist, though one docs page still calls the release pending and names a PyPI package that returns 404 (12).\n- Security \u0026 auth 65: OAuth through Descope with five scopes, and API keys that can be created with a subset of scopes, listed and revoked through the API (30). Read scopes, `validate_only` and `dry_run` on agent changes, a per-run `max_cost_usd` and versioned restores. No confirmation step for deletes or for making a run public (14). Reports are built from untrusted web pages. The docs describe an SSRF-guarded fetch for context files, and no prompt-injection guidance for callers was found (3). Each run has a timeline of execution events, and billing transactions and usage are readable through the API (12). The footer and FAQ claim SOC 2 Type II with no report or trust page linked. security.txt returns 404, and no disclosure policy or bug bounty was found (6). Webhooks are signed with the API key itself.\n- Payments \u0026 pricing 40: No machine payment protocol on the live endpoints. The changelog of 8 May 2026 announces x402 and MPP, and the gateway answered 503 `gateway_disabled` on 8 October 2026 (0). Plan and credit prices are public, but only the medium tier's credit cost is published and the page and its Markdown twin disagree on credits per dollar (10). 100 free trial credits, and 500 for an owner's first agent through AgentID. The pricing page doesn't say whether a card is needed, and its table marks the trial without API access (15). AgentID sign-in is documented as needing no human account, but it depends on an AgentMail inbox and a browser step, and we didn't run it (15).\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 74: @parcha/agentrun 0.2.1 on npm and parcha-agentrun 0.2.1 on PyPI, both on 30 September 2026 (30). Three npm releases of the SDK since 21 September, grep-research-skills 0.2.0 on 4 August, and changelog entries on 11 and 24 July (20). Closed service with a public changelog whose newest entry is 24 July 2026, and support at support@parcha.ai. We didn't test whether support answers (8). Current SDKs in two languages, with docs that lag them. Not found in the official MCP registry (12). The skills repository runs a test workflow. The SDK repositories named in the package metadata asked for credentials, so their CI wasn't read (4).\n- Transparency \u0026 trust 59: Closed service with published terms, written as an order-form contract that still points to grep.parcha.ai. The SDK packages state no licence, and the skills package is MIT (12). Section 12 of the terms says AI providers retain nothing and customer data isn't used for training. Section 4.2 grants a perpetual licence to use customer data to improve the platform, and the privacy policy gives retention only as \"as long as needed\". No DPA found (12). v1 is marked deprecated, /research answers with a `deprecation: true` header and a successor link, and 31 MCP tools are labelled deprecated, all without dates or a written policy (8). The privacy policy names Google Analytics and PostHog and says data may be processed in any country. No subprocessor list found (4).\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (20 items): https://www.anchorterminal.com/fixes/grep-ai.md (JSON https://www.anchorterminal.com/fixes/grep-ai.json)\n\n### What we couldn't check\n\n- unchecked: the MCP tool input schemas and annotations, because tools/list needs an OAuth sign-in. The server card gives names and one-line descriptions only\n- unchecked: whether Free Trial, Pay As You Go or AgentID accounts can call the API or MCP server. The pricing table says API access is Pro and Ultra only, and no account was opened\n- unchecked: whether signup needs a card\n- unchecked: GitHub stars and issue activity, because the GitHub API refused us for its rate limit. The SDK repositories named in the package metadata asked for credentials\n- unchecked: the SOC 2 Type II report, which the footer and FAQ claim without a link\n- Credits per dollar on Pay As You Go. The pricing page says $20 for 200 credits and its Markdown twin says 100\n- Free credits are given as 100 on the pricing page, 1,000 in the FAQ and 500 for AgentID sign-ins\n- Judgement call. The changelog still carries the 8 May 2026 x402 and MPP announcement while the gateway is disabled. We took no deduction because the entry is dated history and the skills README states the gateway isn't generally available\n- The scout wrote that the site doesn't name Parcha. The terms, privacy policy and footer name Parcha Labs, Inc.\n- Category fit is weak. Grep is a hosted agent platform, and search.research covers only the part an outside agent calls for a cited report\n\n### Sources\n\n- llms.txt: \u003chttps://grep.ai/llms.txt\u003e (seen 2026-10-08)\n- OpenAPI document: \u003chttps://api.grep.ai/api/v2/openapi.json\u003e (seen 2026-10-08)\n- developer docs: \u003chttps://grep.ai/developers.md\u003e (seen 2026-10-08)\n- authentication: \u003chttps://grep.ai/developers/api/auth.md\u003e (seen 2026-10-08)\n- errors: \u003chttps://grep.ai/developers/api/errors.md\u003e (seen 2026-10-08)\n- idempotency: \u003chttps://grep.ai/developers/api/idempotency.md\u003e (seen 2026-10-08)\n- pagination: \u003chttps://grep.ai/developers/api/pagination.md\u003e (seen 2026-10-08)\n- webhooks: \u003chttps://grep.ai/developers/api/webhooks.md\u003e (seen 2026-10-08)\n- AgentID sign-in: \u003chttps://grep.ai/developers/api/agentid.md\u003e (seen 2026-10-08)\n- MCP server docs: \u003chttps://grep.ai/developers/mcp.md\u003e (seen 2026-10-08)\n- MCP server card: \u003chttps://grep.ai/.well-known/mcp/server-card.json\u003e (seen 2026-10-08)\n- OAuth protected-resource metadata: \u003chttps://api.grep.ai/.well-known/oauth-protected-resource/mcp\u003e (seen 2026-10-08)\n- A2A agent card: \u003chttps://grep.ai/.well-known/agent-card.json\u003e (seen 2026-10-08)\n- SDK overview: \u003chttps://grep.ai/developers/sdks.md\u003e (seen 2026-10-08)\n- SDK errors and retries: \u003chttps://grep.ai/developers/sdks/errors.md\u003e (seen 2026-10-08)\n- agent onboarding guide: \u003chttps://grep.ai/get-started.md\u003e (seen 2026-10-08)\n- pricing page: \u003chttps://grep.ai/pricing\u003e (seen 2026-10-08)\n- pricing page, Markdown twin: \u003chttps://grep.ai/pricing.md\u003e (seen 2026-10-08)\n- terms of service: \u003chttps://grep.ai/terms\u003e (seen 2026-10-08)\n- privacy policy: \u003chttps://grep.ai/privacy\u003e (seen 2026-10-08)\n- changelog: \u003chttps://grep.ai/changelog\u003e (seen 2026-10-08)\n- FAQ: \u003chttps://grep.ai/faq\u003e (seen 2026-10-08)\n- status page incidents: \u003chttps://status.grep.ai/api/v2/incidents.json\u003e (seen 2026-10-08)\n- public agent list: \u003chttps://api.grep.ai/api/v2/agents\u003e (seen 2026-10-08)\n- payment gateway probe: \u003chttps://api.grep.ai/mpp/v1/api\u003e (seen 2026-10-08)\n- TypeScript SDK on npm: \u003chttps://registry.npmjs.org/@parcha/agentrun\u003e (seen 2026-10-08)\n- skills package on npm: \u003chttps://registry.npmjs.org/grep-research-skills\u003e (seen 2026-10-08)\n- Python SDK on PyPI: \u003chttps://pypi.org/pypi/parcha-agentrun/json\u003e (seen 2026-10-08)\n- skills repository: \u003chttps://github.com/Parcha-ai/grepai-skills\u003e (seen 2026-10-08)\n- MCP registry search: \u003chttps://registry.modelcontextprotocol.io/v0/servers?search=parcha\u003e (seen 2026-10-08)\n- Y Combinator company page: \u003chttps://www.ycombinator.com/companies/grep-ai\u003e (seen 2026-10-08)\n- domain registration: \u003chttps://rdap.identitydigital.services/rdap/domain/grep.ai\u003e (seen 2026-10-08)\n- security.txt: \u003chttps://grep.ai/.well-known/security.txt\u003e (seen 2026-10-08)\n\n## Who's behind it (provenance 82/100, checked 2026-10-08)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | Parcha Labs, Inc. | 20/20 |\n| Domain age | grep.ai, registered 2018-04-20 (8 years) | 11/15 |\n| Endpoint on the vendor's domain | api.grep.ai | 15/15 |\n| Terms of service | read, states 5 of the 7 things a reader expects, and has 1 clause that costs points | 6.3/10 |\n| Privacy policy | read, states 8 of the 8 things a reader expects | 10/10 |\n| Status page | status.grep.ai | 10/10 |\n| Changelog | published | 10/10 |\n| security.txt | not found | 0/10 |\n\nRegistered in 2018 and transferred on 2025-10-19, so the registration date predates the company's use of it.\n\nThe terms of service, last updated 20 March 2026, are a contract with Parcha Labs, Inc., a Delaware corporation, governed by California law.\n\nThe privacy policy, last updated 5 October 2026, names Parcha Labs, Inc. and the websites www.parcha.ai and grep.parcha.ai.\n\nThe API, the MCP server and the A2A endpoint answer on api.grep.ai. OAuth tokens come from Descope at api.descope.com.\n\ngrep.ai/.well-known/security.txt and api.grep.ai/.well-known/security.txt return 404. grep.ai/trust and grep.ai/security return 404.\n\nRDAP for grep.ai gives a registration date of 2018-04-20 and a transfer on 2025-10-19.\n\nThe status page's support link is support@parcha.ai and its privacy link points to parcha.ai.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service** (https://grep.ai/terms), read 2026-10-08, dated 2026-03-20, states 5 of the 7 things a reader expects.\n\n- To know. Restricts automated access (costs points). \"Use any robot, spider, or data scraping tool;\"\n- Gives the date it was last updated. Last updated 2026-03-20.\n- Names the governing law or courts. The law of the State of California.\n- States a limit on its liability. Capped at $100.\n- Not found in the text. Says how changes to the terms are announced.\n- Not found in the text. Refers to a service level or uptime commitment.\n- Also in the text (2026-10-08). Parcha's aggregate liability is capped at 100 US dollars. \"PARCHA’S AGGREGATE LIABILITY SHALL NOT EXCEED ONE HUNDRED DOLLARS ($100).\"\n- Also in the text (2026-10-08). The customer grants a perpetual, irrevocable, transferable and sub-licensable licence to use Customer Data to run the services and to improve the platform. \"Customer hereby grants Parcha a fully paid-up, royalty-free, worldwide, transferable, sub-licensable, irrevocable and perpetual license to use Customer Data to provide the Services and to improve the Platform, and to use all feedback for any purpose.\"\n- Also in the text (2026-10-08). The terms say Parcha will not use Customer Data to train, fine-tune or improve machine learning or AI models. \"PARCHA LABS SHALL NOT USE CUSTOMER DATA FOR THE PURPOSE OF TRAINING, FINE-TUNING, OR IMPROVING MACHINE LEARNING OR ARTIFICIAL INTELLIGENCE MODELS.\"\n\n**Privacy policy** (https://grep.ai/privacy), read 2026-10-08, dated 2026-09-21, states 8 of the 8 things a reader expects.\n\n- To know. Says it sells personal data or shares it for advertising. \"This may constitute a “sale” or “sharing” of personal information under the CCPA/CPRA, even though no money changes hands.\"\n- Gives the date it was last updated. Last updated 2026-09-21.\n- Says how long data is kept. For as long as needed, with no period named.\n- Says whether personal data is sold or shared for advertising. Says it does not sell personal data.\n- Gives a privacy contact. Gives an email address, hidden from our reader by the page.\n- Says where data is transferred or stored. Relies on standard contractual clauses.\n- Also in the text (2026-10-08). Where the platform makes solely automated decisions with legal or similarly significant effects, the policy places responsibility for safeguards on the enterprise customer as data controller. \"our enterprise customers, as the data controllers, are responsible for ensuring that appropriate safeguards are in place, including the right to obtain human intervention, to express a point of view, and to contest the decision.\"\n\n## Live (updated 2026-10-08 18:22 UTC)\n\n- Right now: up, HTTP 401, 186 ms, checked 2026-10-08 18:20 UTC (get on `https://api.grep.ai/api/v2/runs`, asks for auth)\n- Uptime 24h 100.0% (33 probes) · 30 days 100.0% (33 probes) · p50 382 ms · p95 533 ms\n- Vendor status page: none, All Systems Operational\n- github `Parcha-ai/grepai-skills` v0.2.0, released 2026-08-04\n- npm `@parcha/agentrun` 0.2.1\n- npm `grep-research-skills` 0.2.0\n- pypi `parcha-agentrun` 0.2.1, released 2026-09-30\n- security.txt: none\n- Watching changelog \u003chttps://grep.ai/changelog\u003e\n- Watching pricing \u003chttps://grep.ai/pricing\u003e\n- Watching privacy \u003chttps://grep.ai/privacy\u003e\n- Watching terms \u003chttps://grep.ai/terms\u003e\n- Always current: https://www.anchorterminal.com/api/v1/live/grep-ai.json\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Prices\n\n| Item | Price | Unit | Note |\n| --- | --- | --- | --- |\n| Pro plan, 1,500 credits a month, API access | $200 | per month (plan) | $167 a month billed annually |\n| Ultra plan, 4,500 credits a month | $500 | per month (plan) | $417 a month billed annually |\n| Pay As You Go credit | $0.10 | per credit | $20 for 200 credits on the pricing page. Its Markdown twin says 100 credits, which is $0.20. No API access on this plan per the table |\n\nAcross all listings: https://www.anchorterminal.com/prices/index.md\n\n## Strengths\n\n- Public OpenAPI document with 126 operations, llms.txt and a Markdown twin of every developer page\n- OAuth with five scopes, plus API keys that can be minted, scoped and revoked through the API\n- `Idempotency-Key` on run creation, with body-hash matching, a 24-hour replay window and named 409 codes\n- `max_cost_usd` per run, quota pre-flight and batch cost estimates before billable work starts\n- Documented agent sign-in through AgentID with no human account, and 500 free credits for an owner's first agent\n\n## Weaknesses\n\n- No rate limit numbers in the reviewed documentation, and no published SLA\n- The MCP server card lists 82 tools, 31 of them deprecated aliases, with one-line descriptions and no annotations\n- The pricing table marks API access as Pro and Ultra only, from $200 a month\n- The pricing page says $20 buys 200 credits and its Markdown twin says 100. Free credits are stated as 100, 500 and 1,000 on different pages\n- The 8 May 2026 changelog entry announces x402 and MPP payments, but the gateway answered 503 `gateway_disabled` on 8 October 2026\n- No security.txt, trust page, subprocessor list or retention period found. SOC 2 Type II appears only as a footer and FAQ claim\n\n## Before you call it (notes for agents)\n\n1. Send a fresh `Idempotency-Key` with every POST /api/v2/runs. After a timeout, poll the returned run ID and do not post again\n2. Set `effort` and `max_cost_usd` on every run. The floor is $0.50 for low, $2.50 for medium and build, $5.00 for high\n3. Call GET /api/v2/quota/check before a run. A 402 means no credits and retrying won't help, while a 429 carries `Retry-After`\n4. Use the `run_*` and `agent_*` MCP tools. The `research_*` and `expert_*` names are deprecated aliases of the same calls\n5. Treat report text and cited sources as untrusted web content, and verify one load-bearing claim against a primary source\n\n## Connect\n\nInstall:\n\n```bash\nnpm install @parcha/agentrun\n```\n\nFirst request:\n\n```bash\ncurl -X POST \"https://api.grep.ai/api/v2/research\" \\\n -H \"Authorization: Bearer $GREP_API_KEY\" \\\n -H \"Idempotency-Key: 8b9c1f24-3c1e-4a8d-9f7b-2a6e1c4d5b8e\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"question\":\"Due diligence on Stripe\",\"effort\":\"medium\"}'\n```\n\nClaude Code:\n\n```bash\nclaude mcp add --transport http grep https://api.grep.ai/api/v2/mcp\nclaude mcp login grep\n```\n\nMCP client configuration:\n\n```json\n{\n \"mcpServers\": {\n \"grep\": {\n \"url\": \"https://api.grep.ai/api/v2/mcp\"\n }\n }\n}\n```\n\nThrough letme (picks today, calling later): https://letme.dev/grep-ai. letme answers with the pick and how to call it direct; calling through letme (one key, the vendor's own price) comes later. How it works: https://www.anchorterminal.com/letme/index.md\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| Persona | B | 69.5 | 148 | kyc.business, kyc.documents, kyc.screening | no | https://www.anchorterminal.com/tools/persona.md |\n| Sumsub | B | 68.5 | 167 | kyc.business, kyc.documents, kyc.screening | no | https://www.anchorterminal.com/tools/sumsub.md |\n| Trulioo | C | 58.2 | 406 | kyc.business, kyc.documents, kyc.screening | no | https://www.anchorterminal.com/tools/trulioo.md |\n| Tavily API + MCP | BB | 76.8 | 24 | search.answer, search.research | no | https://www.anchorterminal.com/tools/tavily-mcp.md |\n| You.com APIs | BB | 76.5 | 29 | search.answer, search.research | no | https://www.anchorterminal.com/tools/you-com-api.md |\n| Parallel Search and Task APIs | BB | 74 | 65 | search.answer, search.research | no | https://www.anchorterminal.com/tools/parallel-search-api.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- POST /api/v2/runs starts a run at effort low (a quick answer, about 10 to 20 seconds per the schema), medium (a structured report, 2 to 3 minutes), high (8 to 15 minutes) or build, with an optional draft-07 `json_schema` for structured output (source: \u003chttps://api.grep.ai/api/v2/openapi.json\u003e)\n- The MCP server card lists 82 tools and names https://api.grep.ai/mcp as the endpoint, while the docs give https://api.grep.ai/api/v2/mcp. An unauthenticated initialise on the second returned 401 with OAuth resource metadata on 8 October 2026 (source: \u003chttps://grep.ai/.well-known/mcp/server-card.json\u003e)\n- GET /api/v2/agents is public and returned 31 built-in agents on 8 October 2026, among them business and individual AML compliance, corporate due diligence, EIN and proof-of-address document verification (source: \u003chttps://api.grep.ai/api/v2/agents\u003e)\n- Sign in with AgentID gives an agent its own account from an AgentMail inbox and an Ed25519 key, with short-lived tokens and 500 free credits for each owner's first agent (source: \u003chttps://grep.ai/developers/api/agentid\u003e)\n- The x402 and MPP gateway announced in the changelog on 8 May 2026 is switched off. GET https://api.grep.ai/mpp/v1/api returned 503 `gateway_disabled` on 8 October 2026, and the skills package README says the wallet path returns once the gateway is generally available (source: \u003chttps://grep.ai/changelog\u003e)\n- Grep is the product of Parcha Labs, Inc., a Delaware corporation. API keys carry the prefix `parcha-`, and the company launched on Y Combinator's Fall 2026 page on 5 October 2026 with a team of 6 (source: \u003chttps://www.ycombinator.com/companies/grep-ai\u003e)\n- Webhook deliveries are signed with HMAC-SHA256 keyed by the API key itself, retried up to 3 times within a 30-second budget (source: \u003chttps://grep.ai/developers/api/webhooks\u003e)\n\n## Compare\n\n- [Exa API + MCP vs Grep AI](https://www.anchorterminal.com/compare/exa-mcp-vs-grep-ai.md): B 66 vs B 64.4\n- [Grep AI vs Linkup](https://www.anchorterminal.com/compare/grep-ai-vs-linkup.md): B 64.4 vs B 68.9\n- [Grep AI vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/grep-ai-vs-parallel-search-api.md): B 64.4 vs BB 74\n- [Grep AI vs Tavily API + MCP](https://www.anchorterminal.com/compare/grep-ai-vs-tavily-mcp.md): B 64.4 vs BB 76.8\n- [Grep AI vs Valyu](https://www.anchorterminal.com/compare/grep-ai-vs-valyu.md): B 64.4 vs B 64.6\n- [Grep AI vs You.com APIs](https://www.anchorterminal.com/compare/grep-ai-vs-you-com-api.md): B 64.4 vs BB 76.5\n- [Brave Search API + MCP vs Grep AI](https://www.anchorterminal.com/compare/brave-search-mcp-vs-grep-ai.md): B 68 vs B 64.4\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on grep.ai or one of its subdomains, or the README of github.com/Parcha-ai/grepai-skills. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"grep-ai\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/grep-ai\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/grep-ai.svg\" alt=\"Grep AI on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![Grep AI on Anchor Terminal](https://www.anchorterminal.com/badges/grep-ai.svg)](https://www.anchorterminal.com/tools/grep-ai)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/grep-ai\"\u003eGrep AI on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Grep AI is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/grep-ai-dark.png\n- Light: https://www.anchorterminal.com/assets/share/grep-ai-light.png\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-08", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Web search APIs", "url": "https://www.anchorterminal.com/categories/search" }, { "name": "Grep AI", "url": "" } ], "description": "Grep is a hosted platform from Parcha Labs for building and running research agents that return cited reports and structured output. Outside agents reach it through a REST API, a remote MCP server, an A2A endpoint and two SDKs.", "facts": [ "rank #252 of 629", "OAuth or key auth", "0 desk reviews" ], "h1": "Grep AI", "image": "https://www.anchorterminal.com/assets/og/tools-grep-ai.png", "path": "/tools/grep-ai", "published": "2026-10-01", "section": "tools", "title": "Grep AI review for AI agents, grade B (64.4/100) | Anchor Terminal", "toc": null, "updated": "2026-10-08", "url": "https://www.anchorterminal.com/tools/grep-ai" }, "tokens": { "markdown": 7800, "slim": 1830 }, "version": 1 }