The DuckDB-distributed community extension `duckdb_mcp` embeds MCP client and server capabilities directly inside DuckDB. Installers load it via `INSTALL duckdb_mcp FROM community` followed by `LOAD duckdb_mcp`, after which SQL can attach remote MCP servers (stdio/TCP/WebSocket transports), enumerate resources (`mcp_list_resources`), invoke remote tools (`mcp_call_tool`), and wrap responses with `read_csv`/`read_json`/`read_parquet` URIs routed through `mcp://`. In reverse direction, DuckDB can publish tables, queries, and execution-bound tools (`mcp_publish_table`, `mcp_publish_query`, `mcp_publish_execution_tool`) while `mcp_server_start` exposes them to external MCP-compatible clients.
Use cases
- Federating MCP-accessible CSV/JSON/Parquet resources through familiar DuckDB SQL ergonomics
- Publishing deterministic SQL-backed tools agents can orchestrate via MCP servers launched from DuckDB
- Prototyping database-aware agents that need typed tabular pipelines without an extra microservice shim
- Applying allowlists (`allowed_mcp_commands`, `allowed_mcp_urls`) before widening production exposure
- Pairing exploratory analytics workloads with MCP remote tools for preprocessing or enrichment
Key features
- Claude Desktop
- Cursor
- Codex
Frequently Asked Questions
- Who maintains this extension?
- DuckDB’s community-extensions catalog credits maintainer teaguesterling with source hosted on GitHub; it is not the same artifact as Neon or Qdrant standalone MCP binaries.
- How do MCP security knobs work?
- The catalog documents global settings (`allowed_mcp_commands`, `allowed_mcp_urls`, `mcp_lock_servers`, `mcp_disable_serving`, logging paths) alongside development vs production hardening narratives.
- Can DuckDB operate only as client or server?
- Yes—the extension exposes dual modes plus introspection helpers such as `mcp_tools()`, `mcp_resources()`, and `mcp_server_config()` introduced in newer releases documented on the DuckDB extensions page.
Related
Related
3 Indexed items
Neon MCP Server
Official Neon MCP integration exposes Neon Postgres projects to MCP-capable assistants via Streamable HTTP (`https://mcp.neon.tech/mcp`), legacy SSE (`https://mcp.neon.tech/sse`), or a locally launched `@neondatabase/mcp-server-neon` package. Documentation lists tools for project and branch lifecycle, SQL execution, migration rehearsal branches, slow-query diagnostics, Neon Auth provisioning, Data API setup, and embedded Neon docs retrieval—each mapped to Neon API operations.
Postgres MCP
Enables AI agents to execute read-only SQL queries against PostgreSQL databases, inspect table schemas, and analyze query performance. Agents can debug data issues or prepare analytics without requiring direct database credentials in the conversation. Supports connection pooling and multiple database targets.
Postgres MCP
pg-mcp-server is a Model Context Protocol server implementation that connects AI agents to PostgreSQL databases. It registers database schemas as MCP resource templates and exposes SQL execution as an MCP tool. Agents can introspect table structures, run parameterized queries, and manage transactions without leaving the chat interface. Designed as a reference implementation for database MCP integrations.