Skip to content
Agentmart
Submit a tool

Cost Guard MCP

Pre-flight query cost and result-size guardrails for AI agents on BigQuery, Snowflake, Databricks

Connector by mcpsmiths · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 1
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/mcpsmiths-cost-guard-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Pre-flight query cost and result-size guardrails for AI agents on BigQuery, Snowflake, Databricks

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
4 read · 0 write · 0 deleteRead-only
Secrets
6 (API keys, tokens or passwords)
Install scripts
None found
Runs as
Python package

Tools by what they do 4

Read from the source code; the running server may list different tools.

Read 4 · Look things up without changing anything.

  • check_credentials
  • describe_engine_capabilities
  • estimate_query_cost
  • run_query_bounded

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • DATABRICKS_CLIENT_SECRET
  • DATABRICKS_TOKEN
  • GOOGLE_APPLICATION_CREDENTIALS
  • SNOWFLAKE_PASSWORD
  • SNOWFLAKE_PRIVATE_KEY_PASSPHRASE
  • SNOWFLAKE_PRIVATE_KEY_PATH

Other settings (environment variables or headers).

  • COST_GUARD_ALLOW_MULTI_STATEMENT_SQL
  • COST_GUARD_ALLOW_WRITE_STATEMENTS
  • COST_GUARD_DATABRICKS_ALLOW_WAREHOUSE_START
  • COST_GUARD_MAX_IN_FLIGHT_QUERIES
  • COST_GUARD_SNOWFLAKE_ALLOW_WAREHOUSE_RESUME
  • DATABRICKS_CLIENT_ID
  • DATABRICKS_HTTP_PATH
  • DATABRICKS_SERVER_HOSTNAME
  • SNOWFLAKE_ACCOUNT
  • SNOWFLAKE_EDITION
  • SNOWFLAKE_ROLE
  • SNOWFLAKE_SECONDARY_ROLES
Show 1 more settings
  • SNOWFLAKE_USER

Network hosts it talks to 6

  • azure.microsoft.com · found in code
  • cloud.google.com · found in code
  • databricks.com · found in code
  • docs.databricks.com · found in code
  • github.com · found in code
  • snowflake.com · found in code

Tools (4)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • check_credentials

    Verify credentials/connectivity for an engine without running a real query or a dry-run estimate. What runs: BigQuery - one metadata call (the service-account lookup). Snowflake - login, USE WAREHOUSE when a warehouse is given, SELECT CURRENT_WAREHOUSE() when none is, SHOW WAREHOUSES LIKE for the pinned warehouse, and only when that row says STARTED one session-context SELECT. Databricks - one control-plane GET of the configured SQL warehouse (Warehouses API), and only when it is RUNNING a session running SELECT current_user(). Call this once after configuring a new engine (or when a real tool…

  • describe_engine_capabilities

    Declare which cost signals are exact vs. approximate for the given warehouse engine. Call this before estimate_query_cost or run_query_bounded to understand how much to trust the accuracy_tier on their responses for this engine.

  • estimate_query_cost

    Estimate the cost of a SQL query before running it. ALWAYS call this before running an expensive-looking query. The response's accuracy_tier tells you how much to trust the number: PRECISE (exact), UPPER_BOUND (real cap, may overstate), HEURISTIC (rough). Accepts exactly one SQL statement per call (a single trailing ';' is fine) - text with more statements is refused before anything is estimated. This tool accepts only read statements (first keyword SELECT, WITH, VALUES, SHOW, DESCRIBE, DESC or EXPLAIN; a WITH must lead to a SELECT or VALUES) - others are refused before anything is estimated. …

  • run_query_bounded

    Run a query only if its pre-flight cost estimate is within your given bounds; refuses otherwise. Check result.status and result.executed: "refused" with reason "cost_cap_exceeded" or "byte_cap_exceeded" means the query did NOT run (executed=false) and result.hint explains why; "refused" with reason "row_cap_exceeded" or "result_size_exceeded" means the query RAN and was billed (executed=true) and rows holds a truncated prefix of its result - do not re-run it to get more rows, narrow it instead. NOTE: unlike estimate_query_cost, any call with executed=true has a real monetary/quota side effect …

Compare and alternatives

    Featured in

    Signals

    Stars
    1
    Forks
    0
    Open issues
    6
    Weekly downloads
    216
    Last commit
    Oct 19, 2026 (9 days ago)
    Last release
    Oct 19, 2026 (9 days ago)
    Last package publish
    Oct 19, 2026 (9 days ago)

    From GitHub (fetched Oct 24, 2026) and the package registry.

    Details

    Registry name
    io.github.mcpsmiths/cost-guard-mcp
    Version
    0.6.0
    Auth
    API key
    Packages
    pypi cost-guard-mcp
    License
    MIT
    Repository
    github.com/mcpsmiths/cost-guard-mcp
    First seen
    Oct 24, 2026
    Last checked
    Oct 24, 2026
    Source
    Official MCP Registrygithub-graphql

    More from mcpsmiths

    Cite this page

    Cost Guard MCP. Agent Mart. https://agentmart.dev/connectors/mcpsmiths-cost-guard-mcp (last updated 2026-10-24)