BigQuery
This BigQuery MCP server, developed by Salih Ergüt, provides a secure interface for language models to interact with Google BigQuery datasets. It enables AI agents to explore schemas, run SQL queries, and analyze data within configurable limits. The server integrates seamlessly with Claude Desktop, offering a natural language interface to BigQuery's powerful data warehousing capabilities. By focusing on read-only access and built-in safety constraints, it allows AI systems to generate insights from large datasets while maintaining data security. This implementation is particularly useful for AI assistants designed to perform ad-hoc data analysis, generate business intelligence reports, or provide data-driven recommendations using BigQuery as the backend.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/ergut/mcp-bigquery-server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve BigQuery from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.