Skip to main content

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

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

WrapperTypePrimary use
core.agent_discover_contextFunctionDiscover governed tables with scalar filters
core.agent_get_decision_contextFunctionRetrieve governance context for a table
core.agent_inspect_data_meaningFunctionInspect meaning, classification, and masking
core.agent_authorize_useProcedureAsk for an authorization decision
core.agent_validate_query_contextProcedureValidate SQL against governance rules
core.agent_explain_whyProcedureExplain 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:

ToolDescription
discover_contextList governed tables and metadata
get_decision_contextGet the full decision context for a table
inspect_data_meaningInspect classification, masking, and meaning
authorize_useEvaluate whether a proposed data use is allowed
validate_query_contextCheck a SQL query against governance rules
explain_whyRetrieve 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.