--- title: Governed AI at the speed of Snowflake: How Collibra MCP... description: Collibra's Model Context Protocol server connects Snowflake Cortex Agents (CoWork and CoCo) to governed metadata, enabling agents to discover data assets,... canonical: https://daily.dev/posts/governed-ai-at-the-speed-of-snowflake-how-collibra-mcp-powers-snowflake-cowork-coco-kcraoyg9v twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Governed AI at the speed of Snowflake: How Collibra MCP powers Snowflake CoWork & CoCo | daily.dev og:description: Collibra's Model Context Protocol server connects Snowflake Cortex Agents (CoWork and CoCo) to governed metadata, enabling agents to discover data assets,... og:url: https://daily.dev/posts/governed-ai-at-the-speed-of-snowflake-how-collibra-mcp-powers-snowflake-cowork-coco-kcraoyg9v og:image: https://api.daily.dev/og/posts/KcraOyg9V.png og:image:alt: Governed AI at the speed of Snowflake: How Collibra MCP powers Snowflake CoWork & CoCo og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Governed AI at the speed of Snowflake: How Collibra MCP powers Snowflake CoWork & CoCo **[Snowflake Community](https://daily.dev/sources/snowflake_comm)** · 8 min read · 1 upvotes · 0 comments ## Summary Collibra's Model Context Protocol server connects Snowflake Cortex Agents (CoWork and CoCo) to governed metadata, enabling agents to discover data assets, trace lineage, look up business glossary terms, and manage data contracts using natural language, all while respecting per-user OAuth-based role access controls from Collibra. A financial services use case shows a risk analyst using Cortex Agents to verify data certification, trace measure definitions, inspect lineage, and update catalog attributes without leaving Snowflake. The integration is framed as an open, interoperable layer (also usable with Claude, Databricks, and other MCP-compatible platforms) that keeps governance controls intact as AI agents take on more work. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does the Collibra MCP server authenticate users when connected to Snowflake Cortex agents? It uses per-user OAuth 2.0 authentication, meaning each Cortex Agent API call carries the authenticated user's own identity and existing Collibra role-based permissions. A user without access to a sensitive asset in Collibra cannot access it through the agent either, so no separate identity governance layer needs to be built for AI workflows. _Teams wiring AI agents into governed data catalogs can track integration patterns like this via daily.dev._ ### What tools does the Collibra MCP server expose to AI agents? It exposes read tools (like discover_data_assets, get_table_semantics, get_lineage_upstream), write tools (like edit_asset, create_asset, push_data_contract_manifest), and experimental tools that are opt-in and off by default. These span discovery, semantic understanding, lineage tracing, data contracts, and classification/curation across the full data governance lifecycle. _Developers evaluating MCP server capabilities for governed data workflows can follow such tool breakdowns on daily.dev._ ### Who can set up a custom MCP connector for Collibra in Snowflake? Only a user with ACCOUNTADMIN privileges can add the MCP connector in Snowsight under Settings, Account, MCP Connectors, Add Custom. After registration, each individual user authenticates with their own Collibra credentials via OAuth, and once connected, Cortex Agents gain access to all available Collibra tools. _Admins planning enterprise AI-catalog integrations can keep tabs on setup requirements like this through daily.dev._ ## Similar posts on daily.dev - [Snowflake CoCo and CoWork: Governed Context for Agentic AI](https://daily.dev/posts/snowflake-coco-and-cowork-governed-context-for-agentic-ai-uapc0ap69) · Decube · 0 upvotes · 0 comments - [Playing with Snowflake-managed MCP](https://daily.dev/posts/playing-with-snowflake-managed-mcp-tn6no5rel) · Snowflake Community · 1 upvotes · 0 comments - [Governed AI for Every Builder: Enterprise Controls in Snowflake CoCo](https://daily.dev/posts/governed-ai-for-every-builder-enterprise-controls-in-snowflake-coco-uk5mcnnud) · Snowflake · 0 upvotes · 0 comments - [Unlocking Your Data with Snowflake Managed MCP Servers](https://daily.dev/posts/unlocking-your-data-with-snowflake-managed-mcp-servers-xaafduzyx) · Snowflake Community · 0 upvotes · 0 comments - [Snowflake offers help to users and builders of AI agents](https://daily.dev/posts/snowflake-offers-help-to-users-and-builders-of-ai-agents-cyfqdsmlk) · InfoWorld · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#big-data](https://daily.dev/tags/big-data), [#mcp](https://daily.dev/tags/mcp), [#snowflake](https://daily.dev/tags/snowflake) [View this post on daily.dev](https://daily.dev/posts/governed-ai-at-the-speed-of-snowflake-how-collibra-mcp-powers-snowflake-cowork-coco-kcraoyg9v) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Governed AI at the speed of Snowflake: How Collibra MCP powers Snowflake CoWork & CoCo","url":"https://daily.dev/posts/governed-ai-at-the-speed-of-snowflake-how-collibra-mcp-powers-snowflake-cowork-coco-kcraoyg9v","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/governed-ai-at-the-speed-of-snowflake-how-collibra-mcp-powers-snowflake-cowork-coco-kcraoyg9v"},"datePublished":"2026-08-19T17:03:14.916Z","dateModified":"2026-09-14T08:21:14.498Z","description":"Collibra's Model Context Protocol server connects Snowflake Cortex Agents (CoWork and CoCo) to governed metadata, enabling agents to discover data assets,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/eab9d9d46c96785e4e3e3c09b2193ee5?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/eab9d9d46c96785e4e3e3c09b2193ee5?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Snowflake Community","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Snowflake Community","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/3eb5260f70bb4653be0f9581c0d937c8","url":"https://daily.dev/sources/snowflake_comm"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/governed-ai-at-the-speed-of-snowflake-how-collibra-mcp-powers-snowflake-cowork-coco-kcraoyg9v","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,big-data,mcp,snowflake","timeRequired":"PT8M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Snowflake Community","item":"https://daily.dev/sources/snowflake_comm"},{"@type":"ListItem","position":3,"name":"Governed AI at the speed of Snowflake: How Collibra MCP powers Snowflake CoWork & CoCo"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/governed-ai-at-the-speed-of-snowflake-how-collibra-mcp-powers-snowflake-cowork-coco-kcraoyg9v#faq","mainEntity":[{"@type":"Question","name":"How does the Collibra MCP server authenticate users when connected to Snowflake Cortex agents?","acceptedAnswer":{"@type":"Answer","text":"It uses per-user OAuth 2.0 authentication, meaning each Cortex Agent API call carries the authenticated user's own identity and existing Collibra role-based permissions. A user without access to a sensitive asset in Collibra cannot access it through the agent either, so no separate identity governance layer needs to be built for AI workflows. Teams wiring AI agents into governed data catalogs can track integration patterns like this via daily.dev."}},{"@type":"Question","name":"What tools does the Collibra MCP server expose to AI agents?","acceptedAnswer":{"@type":"Answer","text":"It exposes read tools (like discover_data_assets, get_table_semantics, get_lineage_upstream), write tools (like edit_asset, create_asset, push_data_contract_manifest), and experimental tools that are opt-in and off by default. These span discovery, semantic understanding, lineage tracing, data contracts, and classification/curation across the full data governance lifecycle. Developers evaluating MCP server capabilities for governed data workflows can follow such tool breakdowns on daily.dev."}},{"@type":"Question","name":"Who can set up a custom MCP connector for Collibra in Snowflake?","acceptedAnswer":{"@type":"Answer","text":"Only a user with ACCOUNTADMIN privileges can add the MCP connector in Snowsight under Settings, Account, MCP Connectors, Add Custom. After registration, each individual user authenticates with their own Collibra credentials via OAuth, and once connected, Cortex Agents gain access to all available Collibra tools. Admins planning enterprise AI-catalog integrations can keep tabs on setup requirements like this through daily.dev."}}]} ```