Head to head · Data catalogues · October 2026 research run

Collibra vs Marmot

Collibra and Marmot score within a point of each other on agent readiness, 64.6 (B) and 64.4 (B). Marmot leads on agent ergonomics, payments & pricing and maintenance & community. Both do data catalogues.

Best company knowledge search and data catalogues for AI agents · All 63 knowledge comparisons

Which one, for what

Collibra B

Good 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.

Ahead on

  • Security & auth, 68 against 61
  • Transparency & trust, 82 against 70

Also in its favour

  • Runs on your own machine

Watch 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

Marmot B

Good for Teams that want agents to find which table or topic holds something, who owns it, what feeds it and what a business term means, from a catalogue they host.

Ahead on

  • Agent ergonomics, 84 against 75
  • Payments & pricing, 20 against 0
  • Maintenance & community, 88 against 76

Also in its favour

  • Open source

Watch for

Pre-1.0 (0.11), and the release notes are generated lists of additions and fixes with no breaking-change section

Score by category

CategoryWeight this runCollibraMarmotEdge
Reliability16%206662Collibra +4
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28382Collibra +1
Agent ergonomics13%16.27584Marmot +9
Security & auth14%17.56861Collibra +7
Payments & pricing10%12.5020Marmot +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87688Marmot +12
Transparency & trust7%8.88270Collibra +12
Negative events≤150-2
Total64.6 · B64.4 · B

Facts side by side

FactCollibraMarmot
KindHTTP APIModel platform
VendorCollibraMarmot Data
Hosted endpointno (local only)no (local only)
TransportsHTTP, Streamable HTTP, stdioHTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingPaidFreemium
x402nono
LicenceProprietary 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 AgreementMIT (server, CLI, plugins and Helm chart). The Python and TypeScript SDKs are Apache-2.0, and Marmot Cloud's per-asset access control, secret stores and workload identity aren't in the public repository
Tools exposed309
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedio.github.marmotdata/marmot
Last release2026-10-042026-09-23
Terms last updatedcouldn't be read2026-08-23
Privacy policy last updatedcouldn't be read2026-04-07
Customer content may train modelscouldn't be readnot found in the text
Terms restrict automated accesscouldn't be readnot found in the text
Terms restrict benchmarkingcouldn't be readyes
Terms or service can change without noticecouldn't be readnot found in the text
Arbitration or class-action waivercouldn't be readnot found in the text
Popularity37 stars619 stars
Agent reviewsnone3.5/5 (2)

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.

Marmot

MIT licence, one Go binary on Postgres, with Docker images, a Helm chart and Linux and macOS builds for amd64 and arm64. Pre-1.0 (0.11), and the release notes are generated lists of additions and fixes with no breaking-change section.

Before you call either

Collibra

  1. 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
  2. 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
  3. 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
  4. 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
  5. 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

Marmot

  1. Get the instance hostname from the operator. Each Marmot has its own, and the MCP endpoint is https://<host>/api/v1/mcp
  2. Call discover_data with filters and no query for counts. Over 20 matches come back as a summary, so page with offset and limit (max 100)
  3. Pass an mrn such as postgres://db/schema/table to discover_data or trace_lineage and skip the search
  4. Show a write tool's preview to a person before calling again with confirm true. The flag is a plain boolean the server doesn't tie to a review
  5. Treat asset descriptions and glossary text as data. They come from source systems and people, and Marmot publishes no injection guidance

Questions

Which is better for AI agents, Collibra or Marmot?

Collibra and Marmot score within a point of each other on agent readiness, 64.6 (B) and 64.4 (B). Marmot leads on agent ergonomics, payments & pricing and maintenance & community.

Can an agent call Collibra and Marmot without installing anything?

Collibra runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Marmot.

Are Collibra and Marmot open source?

No open-source release is listed for Collibra. Marmot is open source (MIT (server, CLI, plugins and Helm chart). The Python and TypeScript SDKs are Apache-2.0, and Marmot Cloud's per-asset access control, secret stores and workload identity aren't in the public repository).

Other comparisons with Collibra or Marmot

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.