MotherDuck documents a remote Model Context Protocol server at `https://api.motherduck.com/mcp` (fully managed, read-write) that lets Claude, ChatGPT, Cursor, Claude Code, Codex, and other MCP clients query MotherDuck cloud databases via OAuth or Bearer tokens with zero local install per motherduck.com/docs/sql-reference/mcp. Remote tools include read-only `query` and read-write `query_rw` plus schema exploration helpers documented in the MCP workflows guide. For local DuckDB files, S3 paths, or custom limits, the open-source `mcp-server-motherduck` package (motherduckdb/mcp-server-motherduck on GitHub, PyPI `mcp-server-motherduck`) runs via `uvx` with flags such as `--db-path`, `--motherduck-token`, and `--read-write` for self-hosted stdio or HTTP transports.
Use cases
- Let Cursor agents run read-only analytics SQL against MotherDuck warehouses
- Use `query_rw` for governed schema changes from an MCP client with OAuth audit trails
- Query local DuckDB files through the self-hosted server while keeping remote MotherDuck for production
- Switch databases on the fly in local MCP setups per CLI `--switch-databases` flag
- Pair MCP SQL exploration with MotherDuck UI AI features for analyst onboarding
Key features
- Cursor
- Claude Desktop
- Claude Code
- ChatGPT
- Codex
- VS Code
Frequently Asked Questions
- Should new users pick remote or local MCP?
- MotherDuck docs recommend the hosted remote server for most cloud workloads; local mcp-server-motherduck is for DuckDB files, S3, or full customization.
- What is the difference between query and query_rw?
- Workflow docs state `query` is read-only SQL while `query_rw` can modify data or schema on the remote server.
- Does remote MCP access local filesystem DuckDB files?
- No—the comparison table notes local filesystem access is a local-server capability only.
Related
Related
3 Indexed items
MotherDuck MCP Server
MotherDuck documents a remote Model Context Protocol server at motherduck.com/docs/sql-reference/mcp hosted at `https://api.motherduck.com/mcp` with OAuth (or Bearer token) and read-write SQL access to MotherDuck cloud databases. Tools include `list_databases`, `list_tables`, `list_columns`, `search_catalog`, `query`, `query_rw`, `ask_docs_question`, Dive tools (`list_dives`, `read_dive`, `view_dive`, `save_dive`, etc.), and Flight scheduling tools (`list_flights`, `create_flight`, `run_flight`, etc.) per MotherDuck MCP docs. For local DuckDB files or custom configs, MotherDuck points to the open-source `mcp-server-motherduck` package (`uvx mcp-server-motherduck --db-path md:`) on github.com/motherduckdb/mcp-server-motherduck.
ClickHouse Cloud Remote MCP Server
ClickHouse documents a fully managed remote Model Context Protocol server for ClickHouse Cloud at clickhouse.com/docs/cloud/features/ai-ml/remote-mcp. Connect MCP clients to the HTTP endpoint `https://mcp.clickhouse.cloud/mcp` with OAuth 2.0 (browser sign-in with ClickHouse Cloud credentials; no separate API key required per docs). Agents can list databases and tables, inspect schemas, and run scoped read-only SELECT queries; the remote server also exposes richer ClickHouse Cloud integration such as service management, backup monitoring, ClickPipe visibility, and billing data per ClickHouse docs. Enable per service in the Cloud console (Connect → MCP). For self-hosted ClickHouse, ClickHouse maintains the separate open-source mcp-clickhouse project—distinct from this Cloud remote MCP.
BigQuery MCP Server
Google Cloud documents a remote BigQuery Model Context Protocol server at docs.cloud.google.com/bigquery/docs/use-bigquery-mcp, enabled when the BigQuery API is enabled. Connect MCP clients to the managed HTTP endpoint `https://bigquery.googleapis.com/mcp` with OAuth 2.0 and IAM (API keys are not accepted). Documented IAM roles include MCP Tool User (`roles/mcp.toolUser`), BigQuery Job User (`roles/bigquery.jobUser`), and BigQuery Data Viewer (`roles/bigquery.dataViewer`). Tools include `execute_sql` and `execute_sql_readonly` per the use guide; `execute_sql_readonly` allows only read-only operations while `execute_sql` is the sole non-read-only tool. Limitations documented: query processing capped at three minutes by default, results limited to 3,000 rows, and Google Drive external tables unsupported for those SQL tools.