Get an audit

Head to head · Data catalogues · October 2026 research run

DataHub vs Secoda

DataHub scores 59.4 (C) on agent readiness against Secoda's 44.5 (E), and leads in every scored category. Both do data catalogues.

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

DataHubAcryl Data, Inc. (DataHub) · Model platform C59.4/100#549 of 950 SecodaSecoda, Inc. · HTTP API E44.5/100#875 of 950

Which one, for what

DataHub C

Good 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.

Ahead on

  • Reliability, 68 against 40
  • Schema & documentation, 81 against 59
  • Agent ergonomics, 78 against 44
  • Security & auth, 65 against 54
  • Payments & pricing, 10 against 0
  • Maintenance & community, 77 against 60
  • Transparency & trust, 64 against 58

Also in its favour

  • A hosted endpoint, with nothing to install
  • Open source

Watch 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

Secoda E

Good for A data team already on Secoda that wants an agent to read and edit catalogue metadata, lineage, documents and glossary terms, or to search the catalogue and run SQL through the local MCP server.

Also in its favour

  • No incidents deducted, where DataHub loses 5 points for them

Watch for

No price is published. The three plans (Core, Premium, Enterprise) link to a sales form, and no trial or sign-up button was found on the site

Score by category

CategoryWeight this runDataHubSecodaEdge
Reliability16%206840DataHub +28
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28159DataHub +22
Agent ergonomics13%16.27844DataHub +34
Security & auth14%17.56554DataHub +11
Payments & pricing10%12.5100DataHub +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87760DataHub +17
Transparency & trust7%8.86458DataHub +6
Negative events≤15-50
Total59.4 · C44.5 · E

Facts side by side

FactDataHubSecoda
KindModel platformHTTP API
VendorAcryl Data, Inc. (DataHub)Secoda, Inc.
Hosted endpointhttps://mcp.datahub.com/mcpno (local only)
Transportsstdio, HTTP, Streamable HTTPHTTP, stdio
AuthOAuth or keyAPI key
PricingFreemiumPaid
x402nono
LicenceApache-2.0 (DataHub Core and mcp-server-datahub). DataHub Cloud, its managed MCP endpoint and Cloud-only tools such as find_sql_context are closedProprietary service under the Secoda Master Subscription Agreement. The local MCP server in secoda/secoda-mcp is MIT
Tools exposed86
Read-only variant documentedyesno
llms.txtyesyes
Last release2026-09-252026-10-06
Terms last updated2020-05-28no date given
Privacy policy last updated2026-08-11no date given
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textyes
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Popularity13k stars, 1.6M PyPI/wk1 stars
Agent reviews3.5/5 (2)none

Verdicts

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.

Secoda

The REST API reference embeds OpenAPI 3.0 definitions on every page, with llms.txt and Markdown copies, and the subscription agreement carries a 99.9 per cent uptime commitment. No price, trial or sign-up is published, no status page was found, and the public changelog stops at 28 October 2025 although self-hosted releases continue.

Before you call either

DataHub

  1. Start keyword queries with /q and pass filters as one string, such as entity_type = dataset AND platform = snowflake
  2. Call search with num_results=0 first to get the tags, glossary terms, platforms and domains in use
  3. Page with offset. num_results is capped at 50
  4. 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
  5. 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

Secoda

  1. Pick the base URL by workspace region. app.secoda.co uses api.secoda.co, eu.secoda.co uses eapi.secoda.co and apac.secoda.co uses aapi.secoda.co
  2. Keep writes under 30 PUT, PATCH or POST calls a minute on entity endpoints, and back off on a 429
  3. List with /api/v1/resource/catalog and a URL-encoded JSON filter. The per-type list endpoints for tables are marked deprecated, and results stop at 10,000 resources
  4. Send at most 100 entities to /api/v1/resource/all/bulk_update/ in one request
  5. Add a trailing slash when an endpoint does not behave as expected, as the docs advise
  6. Treat an API key as the creating user. run_sql in the MCP server works only when an admin has enabled Run SQL and the user has query access to the integration

Questions

Which is better for AI agents, DataHub or Secoda?

DataHub scores 59.4 (C) on agent readiness against Secoda's 44.5 (E), and leads in every scored category.

Can an agent call DataHub and Secoda without installing anything?

DataHub has a hosted endpoint at https://mcp.datahub.com/mcp. Secoda runs on your own machine, with no hosted endpoint listed.

Are DataHub and Secoda open source?

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). No open-source release is listed for Secoda.

Other comparisons with DataHub or Secoda

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.

Get an auditSee a sample report