{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_9cqbp7q3dudq","handle":"mcp-bigquery-evals","url":"https://wellknown.network/agents/mcp-bigquery-evals","links":{"self":"https://wellknown.network/agents/mcp-bigquery-evals/record.json","html":"https://wellknown.network/agents/mcp-bigquery-evals","markdown":"https://wellknown.network/agents/mcp-bigquery-evals/record.md","api":"https://wellknown.network/api/v1/agents/mcp-bigquery-evals","status":"https://wellknown.network/api/v1/agents/mcp-bigquery-evals/status","claim":"https://wellknown.network/agents/mcp-bigquery-evals/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-bigquery-evals/claim.json","badge":"https://wellknown.network/agents/mcp-bigquery-evals/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-bigquery-evals/history","tools":"https://wellknown.network/api/v1/agents/mcp-bigquery-evals/tools"},"ard":{"identifier":"urn:air::server:mcp-bigquery-evals","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-bigquery-evals","summary":"An MCP server for BigQuery exploration with cost guardrails and a built-in NL→SQL eval harness.","description":"# mcp-bigquery-evals \n \n> An MCP server for BigQuery exploration with cost guardrails and a built-in NL→SQL eval harness. \n \n[![PyPI](https://img.shields.io/pypi/v/mcp-bigquery-evals.svg)](https://pypi.org/project/mcp-bigquery-evals/) \n[![accuracy](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/Umarfarook1/mcp-bigquery-evals/main/evals/badge.json)](#eval-harness) \n[![CI](https://github.com/Umarfarook1/mcp-bigquery-evals/actions/workflows/ci.yml/badge.svg)](https://github.com/Umarfarook1/mcp-bigquery-evals/actions/workflows/ci.yml) \n \n## What it is \n \nA [Model Context Protocol](https://modelcontextprotocol.io/) server that lets Claude Desktop, Cursor, and Claude Code explore and query a BigQuery warehouse safely. \n \n- **7 read-only tools** for warehouse discovery + querying \n- **Mandatory dry-run cost cap** on every `run_query` (default 100 MB scanned, ≈ $0.0005) \n- **Built-in eval harness** with result-set-equivalence methodology — every release ships an accuracy number, not a vibe \n \nTwo clients ship in the box: `RealBigQueryClient` (production) and `FakeBigQueryClient` (in-memory, sqlite-backed; for dev and CI without GCP credentials). \n \n## Quickstart (5 minutes) \n \n### 1. Install \n \n```bash \nuvx mcp-bigquery-evals --help \n``` \n \n(Or `pip install mcp-bigquery-evals` if you prefer.) \n \n### 2. Authenticate to GCP \n \n```bash \ngcloud auth application-default login \n``` \n \n### 3. Add to `claude_desktop_config.json` \n \nOpen Claude Desktop → Settings → Developer → Edit Config, then add: \n \n```json \n{ \n  \"mcpServers\": { \n    \"bigquery\": { \n      \"command\": \"uvx\", \n      \"args\": [\"mcp-bigquery-evals\", \"serve\"], \n      \"env\": { \n        \"BIGQUERY_PROJECT\": \"your-personal-gcp-project-id\" \n      } \n    } \n  } \n} \n``` \n \nRestart Claude Desktop. You should see \"bigquery\" with 7 tools in the MCP indicator. \n \n### 4. Try it \n \nAsk Claude: \n> \"Using the bigquery tool, find the top 5 most-viewed Stack Overflow questions tagged 'python'.\" \n \nClaude will use …","publisher":null,"homepage":"https://github.com/Umarfarook1/mcp-bigquery-evals#readme","repository":"https://github.com/Umarfarook1/mcp-bigquery-evals#readme","version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["mcp","bigquery","llm","nl2sql","claude","evals","agent","tools"],"pricing":null,"endpoints":[{"url":"pypi:mcp-bigquery-evals","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"data.database","name":"Databases","confidence":1,"provenance":"derived"},{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":1,"provenance":"declared"}],"categories":["ai","data"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-bigquery-evals","registry":"pypi","observedAt":"2026-10-28T10:24:14.360Z","publishedAt":"2026-05-02T21:51:20.344946Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-bigquery-evals","url":"https://pypi.org/project/mcp-bigquery-evals/","firstSeenAt":"2026-09-10T00:24:07.046Z","fetchedAt":"2026-10-28T10:22:21.062Z","normalizedAt":"2026-10-28T10:22:21.062Z"}]},"firstSeenAt":"2026-09-10T00:24:07.046Z","updatedAt":"2026-10-28T10:24:14.360Z"}