MCP Tools
The MCP Tools page is now centered on the supported agent workflow for Metatate: Snowflake Intelligence. Metatate still ships a canonical MCP server and six canonical governance tools, but the recommended product path is to use the Snowflake Intelligence adapter wrappers exposed as core.agent_*.
What the page shows
The page is organized into three tabs:
- Connect -- Snowflake Intelligence setup steps, the wrapper tool names, and a first working example
- Test Tools -- direct execution of the canonical Metatate tools using your current Snowflake session
- Docs -- canonical vs adapter-layer explanation, wrapper parameters, and troubleshooting
Connect Tab
The Connect tab no longer walks through Claude, Cursor, or generic MCP client setup. Instead it shows:
- current canonical MCP server registration status
- the supported
core.agent_*wrapper inventory - the exact steps to create a Snowflake Intelligence agent and attach Metatate custom tools
- one practical starter example using
core.agent_get_decision_context
Recommended first test
Attach core.agent_get_decision_context(table_name STRING) to a Snowflake Intelligence agent, then ask:
What governance policies apply to DEV.PUBLIC.LINEITEM?
That validates the Intelligence-to-Metatate path with the fewest moving parts.
Why Snowflake Intelligence uses wrappers
Metatate's canonical SQL tools accept a single VARIANT request payload. Snowflake Intelligence custom tools bind named scalar parameters. Those two interfaces do not line up cleanly, so Metatate provides an adapter layer:
- canonical layer:
core.discover_context(input VARIANT)and peers - Intelligence layer:
core.agent_*wrappers with scalar parameters
The wrapper layer preserves the canonical machine contract while making the tools usable from the Snowflake agent builder UI.
Supported Snowflake Intelligence wrappers
| Wrapper | Type | Primary use |
|---|---|---|
core.agent_discover_context | Function | Discover governed tables with scalar filters |
core.agent_get_decision_context | Function | Retrieve governance context for a table |
core.agent_inspect_data_meaning | Function | Inspect meaning, classification, and masking |
core.agent_authorize_use | Procedure | Ask for an authorization decision |
core.agent_validate_query_context | Procedure | Validate SQL against governance rules |
core.agent_explain_why | Procedure | Explain a logged governance decision |
Test Tools Tab
Test the canonical tools directly from the Metatate UI without configuring a Snowflake Intelligence agent.
Available canonical tools:
| Tool | Description |
|---|---|
discover_context | List governed tables and metadata |
get_decision_context | Get the full decision context for a table |
inspect_data_meaning | Inspect classification, masking, and meaning |
authorize_use | Evaluate whether a proposed data use is allowed |
validate_query_context | Check a SQL query against governance rules |
explain_why | Retrieve the reasoning behind a previous decision |
Docs Tab
The Docs tab explains:
- how the wrapper layer maps onto the canonical tool layer
- which
core.agent_*wrapper to attach for each user intent - the exact parameter names to use in Snowflake Intelligence custom tools
- common failure modes such as accidentally wiring the raw
VARIANT-based canonical tools into an agent
Current scope
This version focuses entirely on Snowflake Intelligence. External-agent connection flows remain technically possible, but they are not the supported product path documented in the app right now.