{ "data": { "a": { "slug": "collibra", "name": "Collibra", "vendor": "Collibra", "vendorUrl": "https://www.collibra.com", "kind": "http-api", "category": "company-knowledge", "summary": "Collibra is a hosted data governance platform with a catalogue, business glossary, lineage and data quality. Agents use REST and GraphQL APIs, a bulk Import API, a hosted MCP server on each cloud instance and an open-source local one.", "url": "https://www.anchorterminal.com/tools/collibra", "markdownUrl": "https://www.anchorterminal.com/tools/collibra.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/collibra.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/collibra.json", "repo": "https://github.com/collibra/chip", "license": "Proprietary service under the Master Collibra Agreement, with the Developer Terms for the REST APIs and CLI. The local MCP server (chip) is Apache-2.0, and the CLI binary ships under a Binary Code Licence Agreement", "transports": [ "http", "streamable-http", "stdio" ], "packages": [], "auth": "mixed", "authNotes": "Access is granted inside a customer's Collibra environment. An administrator with the System administration permission registers an OAuth application under Settings. Integration applications use the client credentials flow at `/rest/oauth/v2/token` and act as an application-specific system user, and user applications use the authorisation code flow with PKCE for MCP clients. Tokens are valid for 5 minutes, and the settings page says Collibra assigns all scopes to the client. The APIs also accept HTTP Basic authentication with a Collibra username and password, and a JWT Bearer token issued by the customer's identity provider. The local MCP server accepts a username and password only. Permissions follow the user's Collibra roles.", "pricing": "paid", "pricingNotes": "No prices are published. www.collibra.com/pricing returns 404, and the site links a demo request and a product tour. We found no trial or self-serve sign-up, so an agent cannot start without a contract. An Evaluation Agreement is published for evaluations arranged with Collibra. The MCP server is free to use, and AI functions such as the natural-language discovery tools consume Collibra Units, with 70,000 or 100,000 units included in each contract depending on the package (checked 2026-10-09).", "priceSummary": "Paid", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the developer portal, the MCP server source or the legal documents (checked 2026-10-09).", "endpoints": [] }, "toolCount": 30, "popularity": { "githubStars": 37, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://developer.collibra.com/", "llmsTxt": "https://developer.collibra.com/llms.txt", "capabilities": [ "data.catalogue", "knowledge.search", "data.lineage" ], "tags": [ "hosted", "closed-source", "enterprise", "official", "mcp", "oauth", "openapi", "graphql", "sales-led", "status-page", "sla", "soc2" ], "lastRelease": "2026-10-04", "graded": true, "anchor": { "graded": true, "score": 64.6, "grade": "B", "agentReady": false, "rank": 346, "ranked": true, "rankOf": 950, "categoryRank": 4, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 76, "payments": 0, "reliability": 66, "schema": 83, "security": 68, "transparency": 82 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-09" }, "negative": 0, "verdict": "Each REST API has an OpenAPI 3.0 definition, the developer portal publishes llms.txt and Markdown pages, and every MCP tool carries read-only and destructive annotations. Access needs a sales contract, since no price, trial or self-serve sign-up is published, and no general API rate limit was found in the reviewed documentation.", "bestFor": "An organisation that already runs Collibra and wants an agent to look up assets, glossary terms, lineage and data quality, or to write assets and classifications under a governed role.", "strengths": [ "OpenAPI 3.0 definitions for each REST API, printed on every reference page of developer.collibra.com and served by each instance at `/docs/index.html`", "The developer portal publishes `llms.txt`, a Markdown copy of every page and an MCP server for searching the documentation", "Every tool in the open-source MCP server declares `readOnlyHint`, `destructiveHint` and `idempotentHint`, and the 18 data quality tools stay unregistered until a flag is set", "OAuth 2.0 client credentials for integrations and an authorisation code flow with PKCE for MCP clients, with access tokens valid for 5 minutes", "A 99.5 per cent monthly uptime target with service credits of 1 to 15 per cent, and an 18-month deprecation period announced for retired REST properties" ], "weaknesses": [ "No published price, trial or self-serve sign-up. The pricing address returns 404 and the site links a demo request and a product tour", "No general request rate limit or `Retry-After` guidance found. Only the OAuth token endpoint has numbers, a pool of 100 tokens refilled at 30 a minute", "The Developer Terms of 22 August 2023 forbid publishing benchmarks and calls not driven by bona fide end user requests, except reasonable testing", "No prompt-injection guidance found, although tools return descriptions and comments written by catalogue users", "The local MCP server signs in with a Collibra username and password only, and `security.txt` expired on 31 December 2025" ], "agentNotes": [ "Ask a Collibra administrator to register an OAuth application. Integration applications use client credentials, and MCP clients need a user application with a redirect URI", "Reuse each access token for its 5 minutes. The token endpoint answers 429 once a client drains its pool of 100 tokens, refilled at 30 a minute", "Page large reads with `cursor=` and `sortField=ID`. Cursor and offset parameters cannot be combined, and Search API `limit` plus `offset` cannot exceed 10,000", "Keep Import API files to 10,000 assets or fewer and run at most 8 imports at once. Retry a job that fails on a concurrency error", "Expect `discover_data_assets` and `discover_business_glossary` to consume Collibra Units and to need the `dgc.ai-copilot` permission. Use `search_asset_keyword` for free keyword search" ], "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": 64.6 } ], "editorialScores": { "ergonomics": 75, "maintenance": 76, "payments": 0, "reliability": 66, "schema": 83, "security": 68, "transparency": 75 }, "provenanceScore": 89 }, "connect": { "http": "curl -H 'Authorization: Bearer \u003ctoken\u003e' https://\u003cinstance\u003e.collibra.com/rest/2.0/communities", "config": { "mcpServers": { "collibra": { "command": "/path/to/chip-...", "type": "stdio" } } } }, "letme": { "capability": "https://letme.dev/data.catalogue", "tool": "https://letme.dev/collibra" }, "area": "business", "provenance": { "legalEntity": "Collibra Inc.", "domain": "collibra.com", "domainRegistered": "2007-06-30", "endpointOnVendorDomain": true, "terms": "https://www.collibra.com/legal/documents/master-collibra-agreement", "privacy": "https://www.collibra.com/legal/documents/collibra-privacy-policy", "statusPage": "https://status.collibra.com", "changelog": "https://productresources.collibra.com/docs/collibra/latest/Content/ReleaseNotes/to_release-notes.htm", "securityTxt": "expired", "checked": "2026-10-09", "notes": [ "The Master Collibra Agreement (click-through version of 6 August 2026) is with Collibra Inc., 28 Liberty Street, Suite 4050, New York, NY 10005 for orders shipped to North America, and with Collibra UK Limited, Broadgate Tower, 20 Primrose Street, London for all others. The second is governed by the law of England and Wales.", "The Developer Terms (22 August 2023) and the Privacy Policy (24 September 2026) name Collibra Belgium BV and its affiliates.", "Each legal page on www.collibra.com is a cover page that links a PDF on images.collibracloud.com. We read the PDFs.", "The Privacy Policy covers Collibra's websites and says it does not apply to personal information Collibra processes for customers. That is governed by the Data Processing Addendum of 1 October 2026 at https://www.collibra.com/legal/documents/collibra-data-processing-addendum.", "www.collibra.com/.well-known/security.txt carries `Expires: 2025-12-31T00:00:00Z`. It names a security requests page and the bug bounty rules.", "RDAP gives collibra.com a registration date of 2007-06-30." ], "score": 89 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/collibra.json", "live": { "slug": "collibra", "vendorStatus": { "page": "https://status.collibra.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-10T00:50:22.042462941Z" }, "versions": [ { "registry": "github", "name": "collibra/chip", "version": "v0.0.47", "released": "2026-08-07", "seenAt": "2026-10-09T16:46:58.350732285Z" } ], "githubStars": 37, "pages": [ { "url": "https://productresources.collibra.com/docs/collibra/latest/Content/ReleaseNotes/to_release-notes.htm", "kind": "changelog", "status": 200, "checkedAt": "2026-10-09T18:44:00.442312281Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "306e62e3e48e" }, { "url": "https://www.collibra.com/legal/documents/collibra-privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-09T18:49:10.565608247Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "f8dfb358e1c5" }, { "url": "https://www.collibra.com/legal/documents/master-collibra-agreement", "kind": "terms", "status": 200, "checkedAt": "2026-10-09T18:49:12.714609966Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "036a1ac5712a" } ], "updatedAt": "2026-10-10T00:50:22.042462941Z" } }, "answer": "Collibra scores 64.6 (B) on agent readiness against DataHub's 59.4 (C), and leads in 3 of 7 scored categories. DataHub leads on payments \u0026 pricing.", "b": { "slug": "datahub", "name": "DataHub", "vendor": "Acryl Data, Inc. (DataHub)", "vendorUrl": "https://datahub.com", "kind": "platform", "category": "company-knowledge", "summary": "Open-source data catalogue and metadata platform from Acryl Data, trading as DataHub.", "url": "https://www.anchorterminal.com/tools/datahub", "markdownUrl": "https://www.anchorterminal.com/tools/datahub.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/datahub.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/datahub.json", "repo": "https://github.com/datahub-project/datahub", "license": "Apache-2.0 (DataHub Core and mcp-server-datahub). DataHub Cloud, its managed MCP endpoint and Cloud-only tools such as find_sql_context are closed", "transports": [ "stdio", "http", "streamable-http" ], "remoteUrl": "https://mcp.datahub.com/mcp", "packages": [ { "registry": "pypi", "name": "mcp-server-datahub" }, { "registry": "oci", "name": "docker.io/acryldata/mcp-server-datahub" }, { "registry": "pypi", "name": "acryl-datahub" } ], "auth": "mixed", "authNotes": "Every DataHub instance takes a personal access token as `Authorization: Bearer`. A token belongs to a user and carries that user's privileges, needs the Generate Personal Access Tokens privilege, and expires after 1 hour to 365 days, with never-expiring tokens off by default. The local MCP server reads `DATAHUB_GMS_URL` and `DATAHUB_GMS_TOKEN` from the environment or `~/.datahubenv`. Its HTTP mode refuses a shared token, takes each client's own bearer token and rejects tokens in the query string. DataHub Cloud's managed endpoint adds OAuth 2.0 with dynamic client registration from Cloud v1.0.2. Tokens have no scopes of their own.", "pricing": "freemium", "pricingNotes": "DataHub Core and the MCP server are Apache-2.0 and free to self-host. DataHub Cloud has no published prices. The Cloud vs Core page says pricing is scoped to the use case, asks you to contact sales, and names a 99.5 per cent uptime SLA. datahub.com/pricing/ returns 404 and we found no free trial (checked 2026-10-03).", "priceSummary": "Freemium", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the Cloud pages or the MCP server source (checked 2026-10-03).", "endpoints": [] }, "toolCount": 8, "popularity": { "githubStars": 12800, "npmWeekly": null, "pypiWeekly": 1634029, "asOf": "2026-10-03" }, "docsUrl": "https://docs.datahub.com/docs/features/feature-guides/mcp", "llmsTxt": "https://docs.datahub.com/llms.txt", "capabilities": [ "data.catalogue", "data.lineage", "work.docs" ], "tags": [ "open-source", "self-hosted", "hosted", "mcp", "oauth", "llms-txt", "python", "java", "docker", "freemium", "enterprise", "read-only-mode", "telemetry-default-on", "pre-1.0", "status-page" ], "lastRelease": "2026-09-25", "graded": true, "anchor": { "graded": true, "score": 59.4, "grade": "C", "agentReady": false, "rank": 549, "ranked": true, "rankOf": 950, "categoryRank": 9, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 77, "payments": 10, "reliability": 68, "schema": 81, "security": 65, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-03" }, "negative": -5, "negativeNotes": [ "2026-03-11. Since the modular rewrite synced on 11 March 2026, every mcp-server-datahub tool call sends a Mixpanel event, on by default, with the tool name, the MCP client's name and version (added 16 March), result length, duration and the first 500 characters of any error message. The telemetry page lists CLI invocations and error types, and neither it, the README nor the MCP docs mention MCP tool calls. Error text can carry URNs from the catalogue, so more than counts, -3 (https://github.com/acryldata/mcp-server-datahub/blob/main/src/mcp_server_datahub/_telemetry.py; https://github.com/datahub-project/datahub/blob/master/docs/deploy/telemetry.md)", "2026-02-04 to 2026-05-19. Four advisories in twelve months, CVE-2026-25644 (7.5, the LDAP ingestion source turned off TLS certificate checks, fixed in 1.3.1.8), CVE-2026-44501 (4.3, cookie deserialisation in the OIDC callback, fixed in 1.5.0.3) and two open redirects. All fixed and published, so decayed, -2 (https://github.com/datahub-project/datahub/security/advisories)" ], "verdict": "Apache-2.0 platform and MCP server, run with `uvx mcp-server-datahub@latest` or the acryldata/mcp-server-datahub Docker image against DataHub Core or DataHub Cloud. The eight default tools carry about 26,000 characters of descriptions, and search and get_lineage each repeat the same 3,063-character filter grammar.", "bestFor": "Teams already running DataHub who want agents to find tables, trace column lineage, read the SQL people run and see owners and glossary terms before touching data.", "strengths": [ "Apache-2.0 platform and MCP server, run with `uvx mcp-server-datahub@latest` or the acryldata/mcp-server-datahub Docker image against DataHub Core or DataHub Cloud", "Write tools stay off until `TOOLS_IS_MUTATION_ENABLED=true`, and all 10 read tools carry readOnlyHint", "One filter string on search and lineage (`platform = snowflake AND env = PROD`), paging capped at 50, facet-only searches and an 80,000-token response budget", "The shared HTTP mode refuses a server-wide token, takes each user's own bearer token in the header only and rejects tokens in the query string", "CI runs unit tests and integration tests against DataHub quickstarts for Cloud, v1.3.0 and head, passing on main, and DataHub tagged five releases between 4 August and 25 September 2026" ], "weaknesses": [ "The eight default tools carry about 26,000 characters of descriptions, and search and get_lineage each repeat the same 3,063-character filter grammar", "Every tool call sends a Mixpanel event by default with the tool name, the client and up to 500 characters of any error message, and no docs page mentions it", "The MCP server is pre-1.0 (0.7.1), and CHANGELOG.md stops at 0.5.3 with a breaking HTTP change still under Unreleased", "The docs page lists Cloud-only tools such as find_sql_context and says every tool carries destructiveHint and idempotentHint, which the open-source server doesn't set", "No published DataHub Cloud prices or trial, no DPA or subprocessor list, and the privacy policy excludes paying customers' use of the service" ], "agentNotes": [ "Start keyword queries with `/q` and pass filters as one string, such as `entity_type = dataset AND platform = snowflake`", "Call `search` with `num_results=0` first to get the tags, glossary terms, platforms and domains in use", "Page with `offset`. `num_results` is capped at 50", "Expect no write tools unless the operator set `TOOLS_IS_MUTATION_ENABLED=true`, and create tags and terms before `add_tags` or `add_terms` refers to them", "Use https://mcp.datahub.com/mcp with OAuth only on DataHub Cloud v1.0.2 or later. DataHub Core needs the local server and a personal access token" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59.4 } ], "editorialScores": { "ergonomics": 78, "maintenance": 77, "payments": 10, "reliability": 68, "schema": 81, "security": 65, "transparency": 55 }, "provenanceScore": 72 }, "connect": { "install": "uvx mcp-server-datahub@latest", "claudeCode": "claude mcp add datahub \\\n -e DATAHUB_GMS_URL=\"\u003cyour-datahub-url\u003e\" \\\n -e DATAHUB_GMS_TOKEN=\"\u003cyour-datahub-token\u003e\" \\\n -- uvx mcp-server-datahub@latest", "config": { "mcpServers": { "datahub": { "args": [ "mcp-server-datahub@latest" ], "command": "\u003cfull-path-to-uvx\u003e", "env": { "DATAHUB_GMS_TOKEN": "\u003cyour-datahub-token\u003e", "DATAHUB_GMS_URL": "\u003cyour-datahub-url\u003e" } } } } }, "letme": { "capability": "https://letme.dev/data.catalogue", "tool": "https://letme.dev/datahub" }, "area": "business", "provenance": { "legalEntity": "Acryl Data, Inc. (d/b/a DataHub)", "domain": "datahub.com", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://datahub.com/terms-of-service/", "privacy": "https://datahub.com/privacy-policy/", "statusPage": "https://status.datahub.com", "changelog": "https://github.com/datahub-project/datahub/releases", "securityTxt": "none", "checked": "2026-10-03", "notes": [ "The datahub.com footer reads Acryl Data, Inc., and the privacy policy of 11 August 2026 names Acryl Data, Inc. d/b/a DataHub.", "The terms of service (28 May 2020) cover the website only. Paid use is governed by a Master Services Agreement we couldn't read.", "The shared managed MCP endpoint is mcp.datahub.com, and tenant endpoints sit on \u003ctenant\u003e.acryl.io. A self-hosted MCP server answers on the operator's own host.", "datahub.com/.well-known/security.txt returns 404. SECURITY.md routes reports to security@datahub.com with a PGP key, and advisories are published on GitHub.", "status.datahub.com runs on incident.io with one component, DataHub Cloud, and history from July 2026." ], "score": 72 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/datahub.json", "live": { "slug": "datahub", "probe": { "target": "https://mcp.datahub.com/mcp", "method": "get", "lastAt": "2026-10-10T02:07:06.555823402Z", "lastOk": true, "lastStatus": 401, "lastMs": 684, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 760, "p95ms24h": 1761, "samples24h": 250, "samples30d": 1682, "days": [ { "date": "2026-10-03", "probes": 54, "ok": 54 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 22, "ok": 22 } ] }, "vendorStatus": { "page": "https://status.datahub.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-10T02:05:53.396432985Z" }, "versions": [ { "registry": "github", "name": "datahub-project/datahub", "version": "v1.7.0.1", "released": "2026-09-03", "seenAt": "2026-10-09T16:48:35.176498673Z" }, { "registry": "pypi", "name": "acryl-datahub", "version": "1.7.0.14", "released": "2026-09-29", "seenAt": "2026-10-09T16:48:33.359176074Z" }, { "registry": "pypi", "name": "mcp-server-datahub", "version": "0.7.1", "released": "2026-09-16", "seenAt": "2026-10-09T16:48:33.132097113Z" } ], "githubStars": 12806, "pypiWeekly": 7126, "securityTxt": { "url": "https://datahub.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-09T15:39:21.985888429Z" }, "llmsTxt": { "url": "https://docs.datahub.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-09T14:01:46.88361941Z" }, "domain": { "domain": "datahub.com", "registered": "1995-03-16", "source": "https://rdap.verisign.com/com/v1/domain/datahub.com", "checkedAt": "2026-10-04T13:10:21.931110985Z" }, "pages": [ { "url": "https://datahub.com/privacy-policy/", "kind": "privacy", "status": 200, "checkedAt": "2026-10-09T18:34:41.075657227Z", "changedAt": "2026-10-09T18:34:41.075657227Z", "fingerprint": "6388daf5bf14" }, { "url": "https://datahub.com/terms-of-service/", "kind": "terms", "status": 200, "checkedAt": "2026-10-09T18:34:44.210069227Z", "changedAt": "2026-10-09T18:34:44.210069227Z", "fingerprint": "ac2dc4c6d076" } ], "updatedAt": "2026-10-10T02:07:06.555823402Z" } }, "facts": [ { "a": "HTTP API", "b": "Model platform", "name": "Kind" }, { "a": "Collibra", "b": "Acryl Data, Inc. (DataHub)", "name": "Vendor" }, { "a": "no (local only)", "b": "https://mcp.datahub.com/mcp", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP, stdio", "b": "stdio, HTTP, Streamable HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth or key", "name": "Auth" }, { "a": "Paid", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the Master Collibra Agreement, with the Developer Terms for the REST APIs and CLI. The local MCP server (chip) is Apache-2.0, and the CLI binary ships under a Binary Code Licence Agreement", "b": "Apache-2.0 (DataHub Core and mcp-server-datahub). DataHub Cloud, its managed MCP endpoint and Cloud-only tools such as find_sql_context are closed", "name": "Licence" }, { "a": "30", "b": "8", "name": "Tools exposed" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-04", "b": "2026-09-25", "name": "Last release" }, { "a": "couldn't be read", "b": "2020-05-28", "name": "Terms last updated" }, { "a": "couldn't be read", "b": "2026-08-11", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "37 stars", "b": "13k stars, 1.6M PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3.5/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Collibra scores 64.6 (B) on agent readiness against DataHub's 59.4 (C), and leads in 3 of 7 scored categories. DataHub leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Collibra or DataHub?" }, { "answer": "Collibra runs on your own machine, with no hosted endpoint listed. DataHub has a hosted endpoint at https://mcp.datahub.com/mcp.", "question": "Can an agent call Collibra and DataHub without installing anything?" }, { "answer": "No open-source release is listed for Collibra. DataHub is open source (Apache-2.0 (DataHub Core and mcp-server-datahub). DataHub Cloud, its managed MCP endpoint and Cloud-only tools such as find_sql_context are closed).", "question": "Are Collibra and DataHub open source?" } ], "goodFor": [ { "aheadOn": [ "Transparency \u0026 trust, 82 against 64" ], "also": [ "No incidents deducted, where DataHub loses 5 points for them" ], "goodFor": "An organisation that already runs Collibra and wants an agent to look up assets, glossary terms, lineage and data quality, or to write assets and classifications under a governed role.", "slug": "collibra", "watchFor": "No published price, trial or self-serve sign-up. The pricing address returns 404 and the site links a demo request and a product tour" }, { "aheadOn": [ "Payments \u0026 pricing, 10 against 0" ], "also": [ "A hosted endpoint, with nothing to install", "Open source" ], "goodFor": "Teams already running DataHub who want agents to find tables, trace column lineage, read the SQL people run and see owners and glossary terms before touching data.", "slug": "datahub", "watchFor": "The eight default tools carry about 26,000 characters of descriptions, and search and get_lineage each repeat the same 3,063-character filter grammar" } ], "job": { "capability": "data.catalogue", "name": "Data catalogues" }, "others": [ { "json": "https://www.anchorterminal.com/compare/cohere-north-vs-collibra.json", "title": "Cohere North vs Collibra", "url": "https://www.anchorterminal.com/compare/cohere-north-vs-collibra" }, { "json": "https://www.anchorterminal.com/compare/collibra-vs-dust.json", "title": "Collibra vs Dust", "url": "https://www.anchorterminal.com/compare/collibra-vs-dust" }, { "json": "https://www.anchorterminal.com/compare/collibra-vs-glean.json", "title": "Collibra vs Glean", "url": "https://www.anchorterminal.com/compare/collibra-vs-glean" }, { "json": "https://www.anchorterminal.com/compare/collibra-vs-guru.json", "title": "Collibra vs Guru", "url": "https://www.anchorterminal.com/compare/collibra-vs-guru" }, { "json": "https://www.anchorterminal.com/compare/collibra-vs-onyx.json", "title": "Collibra vs Onyx", "url": "https://www.anchorterminal.com/compare/collibra-vs-onyx" }, { "json": "https://www.anchorterminal.com/compare/collibra-vs-overclock.json", "title": "Collibra vs Overclock", "url": "https://www.anchorterminal.com/compare/collibra-vs-overclock" }, { "json": "https://www.anchorterminal.com/compare/alation-vs-collibra.json", "title": "Alation vs Collibra", "url": "https://www.anchorterminal.com/compare/alation-vs-collibra" }, { "json": "https://www.anchorterminal.com/compare/alation-vs-datahub.json", "title": "Alation vs DataHub", "url": "https://www.anchorterminal.com/compare/alation-vs-datahub" }, { "json": "https://www.anchorterminal.com/compare/atlan-vs-collibra.json", "title": "Atlan vs Collibra", "url": "https://www.anchorterminal.com/compare/atlan-vs-collibra" }, { "json": "https://www.anchorterminal.com/compare/atlan-vs-datahub.json", "title": "Atlan vs DataHub", "url": "https://www.anchorterminal.com/compare/atlan-vs-datahub" }, { "json": "https://www.anchorterminal.com/compare/collibra-vs-marmot.json", "title": "Collibra vs Marmot", "url": "https://www.anchorterminal.com/compare/collibra-vs-marmot" }, { "json": "https://www.anchorterminal.com/compare/collibra-vs-openmetadata.json", "title": "Collibra vs OpenMetadata", "url": "https://www.anchorterminal.com/compare/collibra-vs-openmetadata" }, { "json": "https://www.anchorterminal.com/compare/collibra-vs-secoda.json", "title": "Collibra vs Secoda", "url": "https://www.anchorterminal.com/compare/collibra-vs-secoda" }, { "json": "https://www.anchorterminal.com/compare/datahub-vs-marmot.json", "title": "DataHub vs Marmot", "url": "https://www.anchorterminal.com/compare/datahub-vs-marmot" }, { "json": "https://www.anchorterminal.com/compare/datahub-vs-openmetadata.json", "title": "DataHub vs OpenMetadata", "url": "https://www.anchorterminal.com/compare/datahub-vs-openmetadata" }, { "json": "https://www.anchorterminal.com/compare/datahub-vs-secoda.json", "title": "DataHub vs Secoda", "url": "https://www.anchorterminal.com/compare/datahub-vs-secoda" }, { "json": "https://www.anchorterminal.com/compare/datahub-vs-guru.json", "title": "DataHub vs Guru", "url": "https://www.anchorterminal.com/compare/datahub-vs-guru" } ], "scores": [ { "by": 2, "collibra": 66, "datahub": 68, "edge": "datahub", "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 2, "collibra": 83, "datahub": 81, "edge": "collibra", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 3, "collibra": 75, "datahub": 78, "edge": "datahub", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 3, "collibra": 68, "datahub": 65, "edge": "collibra", "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 10, "collibra": 0, "datahub": 10, "edge": "datahub", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 1, "collibra": 76, "datahub": 77, "edge": "datahub", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 18, "collibra": 82, "datahub": 64, "edge": "collibra", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Collibra scores 64.6 (B) on agent readiness against DataHub's 59.4 (C), and leads in 3 of 7 scored categories. DataHub leads on payments \u0026 pricing. Both do data catalogues.", "verdicts": { "collibra": "Each REST API has an OpenAPI 3.0 definition, the developer portal publishes llms.txt and Markdown pages, and every MCP tool carries read-only and destructive annotations. Access needs a sales contract, since no price, trial or self-serve sign-up is published, and no general API rate limit was found in the reviewed documentation.", "datahub": "Apache-2.0 platform and MCP server, run with `uvx mcp-server-datahub@latest` or the acryldata/mcp-server-datahub Docker image against DataHub Core or DataHub Cloud. The eight default tools carry about 26,000 characters of descriptions, and search and get_lineage each repeat the same 3,063-character filter grammar." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/collibra-vs-datahub", "json": "https://www.anchorterminal.com/compare/collibra-vs-datahub.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/collibra-vs-datahub.md", "slim": "https://www.anchorterminal.com/compare/collibra-vs-datahub.min.md" }, "markdown": "Collibra scores 64.6 (B) on agent readiness against DataHub's 59.4 (C), and leads in 3 of 7 scored categories. DataHub leads on payments \u0026 pricing. Both do data catalogues.\n\n- Collibra: grade B, 64.6/100, rank #346 of 950. Markdown https://www.anchorterminal.com/tools/collibra.md · JSON https://www.anchorterminal.com/api/v1/tools/collibra.json\n- DataHub: grade C, 59.4/100, rank #549 of 950. Markdown https://www.anchorterminal.com/tools/datahub.md · JSON https://www.anchorterminal.com/api/v1/tools/datahub.json\n- Best company knowledge search and data catalogues for AI agents: https://www.anchorterminal.com/best/company-knowledge/index.md\n- All 63 knowledge comparisons: https://www.anchorterminal.com/compare/company-knowledge/index.md\n\n## Which one, for what\n\n### Collibra (B)\n\nGood for: An organisation that already runs Collibra and wants an agent to look up assets, glossary terms, lineage and data quality, or to write assets and classifications under a governed role.\n\nAhead on:\n- Transparency \u0026 trust, 82 against 64\n\nAlso in its favour:\n- No incidents deducted, where DataHub loses 5 points for them\n\nWatch for: No published price, trial or self-serve sign-up. The pricing address returns 404 and the site links a demo request and a product tour\n\n### DataHub (C)\n\nGood for: Teams already running DataHub who want agents to find tables, trace column lineage, read the SQL people run and see owners and glossary terms before touching data.\n\nAhead on:\n- Payments \u0026 pricing, 10 against 0\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Open source\n\nWatch for: The eight default tools carry about 26,000 characters of descriptions, and search and get_lineage each repeat the same 3,063-character filter grammar\n\n\n## Score by category\n\n| Category | Weight | Collibra | DataHub | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 66 | 68 | DataHub +2 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 83 | 81 | Collibra +2 |\n| Agent ergonomics | 13% (16.2 this run) | 75 | 78 | DataHub +3 |\n| Security \u0026 auth | 14% (17.5 this run) | 68 | 65 | Collibra +3 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 0 | 10 | DataHub +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 76 | 77 | DataHub +1 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 82 | 64 | Collibra +18 |\n| Negative events | ≤15 | 0 | -5 | |\n| **Total** | | **64.6 · B** | **59.4 · C** | |\n\n## Facts side by side\n\n| Fact | Collibra | DataHub |\n| --- | --- | --- |\n| Kind | HTTP API | Model platform |\n| Vendor | Collibra | Acryl Data, Inc. (DataHub) |\n| Hosted endpoint | no (local only) | `https://mcp.datahub.com/mcp` |\n| Transports | HTTP, Streamable HTTP, stdio | stdio, HTTP, Streamable HTTP |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Paid | Freemium |\n| x402 | no | no |\n| Licence | Proprietary service under the Master Collibra Agreement, with the Developer Terms for the REST APIs and CLI. The local MCP server (chip) is Apache-2.0, and the CLI binary ships under a Binary Code Licence Agreement | Apache-2.0 (DataHub Core and mcp-server-datahub). DataHub Cloud, its managed MCP endpoint and Cloud-only tools such as find_sql_context are closed |\n| Tools exposed | 30 | 8 |\n| Read-only variant documented | no | yes |\n| llms.txt | yes | yes |\n| Last release | 2026-10-04 | 2026-09-25 |\n| Terms last updated | couldn't be read | 2020-05-28 |\n| Privacy policy last updated | couldn't be read | 2026-08-11 |\n| Customer content may train models | couldn't be read | not found in the text |\n| Terms restrict automated access | couldn't be read | not found in the text |\n| Terms restrict benchmarking | couldn't be read | not found in the text |\n| Terms or service can change without notice | couldn't be read | not found in the text |\n| Arbitration or class-action waiver | couldn't be read | not found in the text |\n| Popularity | 37 stars | 13k stars, 1.6M PyPI/wk |\n| Agent reviews | none | 3.5/5 (2) |\n\n## Verdicts\n\n**Collibra.** Each REST API has an OpenAPI 3.0 definition, the developer portal publishes llms.txt and Markdown pages, and every MCP tool carries read-only and destructive annotations. Access needs a sales contract, since no price, trial or self-serve sign-up is published, and no general API rate limit was found in the reviewed documentation.\n\n**DataHub.** Apache-2.0 platform and MCP server, run with `uvx mcp-server-datahub@latest` or the acryldata/mcp-server-datahub Docker image against DataHub Core or DataHub Cloud. The eight default tools carry about 26,000 characters of descriptions, and search and get_lineage each repeat the same 3,063-character filter grammar.\n\n## Before you call either\n\n### Collibra\n\n1. Ask a Collibra administrator to register an OAuth application. Integration applications use client credentials, and MCP clients need a user application with a redirect URI\n2. Reuse each access token for its 5 minutes. The token endpoint answers 429 once a client drains its pool of 100 tokens, refilled at 30 a minute\n3. Page large reads with `cursor=` and `sortField=ID`. Cursor and offset parameters cannot be combined, and Search API `limit` plus `offset` cannot exceed 10,000\n4. Keep Import API files to 10,000 assets or fewer and run at most 8 imports at once. Retry a job that fails on a concurrency error\n5. Expect `discover_data_assets` and `discover_business_glossary` to consume Collibra Units and to need the `dgc.ai-copilot` permission. Use `search_asset_keyword` for free keyword search\n\n### DataHub\n\n1. Start keyword queries with `/q` and pass filters as one string, such as `entity_type = dataset AND platform = snowflake`\n2. Call `search` with `num_results=0` first to get the tags, glossary terms, platforms and domains in use\n3. Page with `offset`. `num_results` is capped at 50\n4. Expect no write tools unless the operator set `TOOLS_IS_MUTATION_ENABLED=true`, and create tags and terms before `add_tags` or `add_terms` refers to them\n5. Use https://mcp.datahub.com/mcp with OAuth only on DataHub Cloud v1.0.2 or later. DataHub Core needs the local server and a personal access token\n\n## Questions\n\n### Which is better for AI agents, Collibra or DataHub?\n\nCollibra scores 64.6 (B) on agent readiness against DataHub's 59.4 (C), and leads in 3 of 7 scored categories. DataHub leads on payments \u0026 pricing.\n\n### Can an agent call Collibra and DataHub without installing anything?\n\nCollibra runs on your own machine, with no hosted endpoint listed. DataHub has a hosted endpoint at https://mcp.datahub.com/mcp.\n\n### Are Collibra and DataHub open source?\n\nNo open-source release is listed for Collibra. DataHub is open source (Apache-2.0 (DataHub Core and mcp-server-datahub). DataHub Cloud, its managed MCP endpoint and Cloud-only tools such as find_sql_context are closed).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/collibra-vs-datahub.json, and with the fewest tokens: https://www.anchorterminal.com/compare/collibra-vs-datahub.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"collibra\", \"b\": \"datahub\"}`. From a terminal: `anchor compare collibra datahub`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/collibra.json and https://www.anchorterminal.com/api/v1/tools/datahub.json\n\n## Other comparisons with Collibra or DataHub\n\n- [Cohere North vs Collibra](https://www.anchorterminal.com/compare/cohere-north-vs-collibra.md)\n- [Collibra vs Dust](https://www.anchorterminal.com/compare/collibra-vs-dust.md)\n- [Collibra vs Glean](https://www.anchorterminal.com/compare/collibra-vs-glean.md)\n- [Collibra vs Guru](https://www.anchorterminal.com/compare/collibra-vs-guru.md)\n- [Collibra vs Onyx](https://www.anchorterminal.com/compare/collibra-vs-onyx.md)\n- [Collibra vs Overclock](https://www.anchorterminal.com/compare/collibra-vs-overclock.md)\n- [Alation vs Collibra](https://www.anchorterminal.com/compare/alation-vs-collibra.md)\n- [Alation vs DataHub](https://www.anchorterminal.com/compare/alation-vs-datahub.md)\n- [Atlan vs Collibra](https://www.anchorterminal.com/compare/atlan-vs-collibra.md)\n- [Atlan vs DataHub](https://www.anchorterminal.com/compare/atlan-vs-datahub.md)\n- [Collibra vs Marmot](https://www.anchorterminal.com/compare/collibra-vs-marmot.md)\n- [Collibra vs OpenMetadata](https://www.anchorterminal.com/compare/collibra-vs-openmetadata.md)\n- [Collibra vs Secoda](https://www.anchorterminal.com/compare/collibra-vs-secoda.md)\n- [DataHub vs Marmot](https://www.anchorterminal.com/compare/datahub-vs-marmot.md)\n- [DataHub vs OpenMetadata](https://www.anchorterminal.com/compare/datahub-vs-openmetadata.md)\n- [DataHub vs Secoda](https://www.anchorterminal.com/compare/datahub-vs-secoda.md)\n- [DataHub vs Guru](https://www.anchorterminal.com/compare/datahub-vs-guru.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-10", "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": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Collibra vs DataHub", "url": "" } ], "description": "Collibra scores 64.6 (B) to DataHub's 59.4 (C) for data catalogues. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Collibra B 64.6", "DataHub C 59.4", "scores" ], "h1": "Collibra vs DataHub", "image": "https://www.anchorterminal.com/assets/og/compare-collibra-vs-datahub.png", "path": "/compare/collibra-vs-datahub", "published": "2026-10-01", "section": "tools", "title": "Collibra vs DataHub for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/collibra-vs-datahub" }, "tokens": { "markdown": 2400, "slim": 830 }, "version": 1 }