databasesanalytics-data

MotherDuck & DuckDB

by motherduckdb

Integrates MotherDuck and local DuckDB for flexible querying and analysis of structured data in MCP-compatible environme

Integrates MotherDuck and local DuckDB databases for flexible querying and analysis of structured data in MCP-compatible environments.

github stars

435

Works with local files and cloud databasesRead-only mode by default for securityAlternative to fully-managed remote option

best for

  • / Data analysts querying structured datasets
  • / SQL analytics through AI assistants
  • / Data engineering workflows
  • / Cross-database querying between local and cloud

capabilities

  • / Execute SQL queries on DuckDB databases
  • / Query local DuckDB files and in-memory databases
  • / Connect to MotherDuck cloud databases
  • / Access S3-hosted DuckDB databases
  • / Switch between database connections
  • / Browse database catalogs and schemas

what it does

Connects AI assistants to DuckDB databases (local, MotherDuck, or S3) for SQL analytics and data queries.

how to install

You can install MotherDuck & DuckDB in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.

license

MIT

MotherDuck & DuckDB is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.

readme

MotherDuck / DuckDB Local MCP Server

DuckDB / MotherDuck Local MCP Server

SQL analytics and data engineering for AI Assistants and IDEs.

--- Connect AI assistants to your data using DuckDB's powerful analytical SQL engine. Supports connecting to local DuckDB files, in-memory databases, S3-hosted databases, and MotherDuck. Allows executing SQL read- and write-queries, browsing database catalogs, and switching between different database connections on-the-fly. **Looking for a fully-managed remote MCP server for MotherDuck?** → [Go to the MotherDuck Remote MCP docs](https://motherduck.com/docs/sql-reference/mcp/) ### Remote vs Local MCP | | **[Remote MCP](https://motherduck.com/docs/sql-reference/mcp/)** | **Local MCP** (this repo) | |---|---|---| | **Hosting** | Hosted by MotherDuck | Runs locally/self-hosted | | **Setup** | Zero-setup | Requires local installation | | **Access** | Read-write supported | Read-write supported | | **Local filesystem** | - | Query across local and remote databases, ingest data from / export data to local filesystem | > 📝 **Migrating from v0.x?** > - **Read-only by default**: The server now runs in read-only mode by default. Add `--read-write` to enable write access. See [Securing for Production](#securing-for-production). > - **Default database changed**: `--db-path` default changed from `md:` to `:memory:`. Add `--db-path md:` explicitly for MotherDuck. > - **MotherDuck read-only requires read-scaling token**: MotherDuck connections in read-only mode require a [read-scaling token](https://motherduck.com/docs/key-tasks/authenticating-and-connecting-to-motherduck/authenticating-to-motherduck/#read-scaling-tokens). Regular tokens require `--read-write`. ## Quick Start **Prerequisites**: Install `uv` via `pip install uv` or `brew install uv` ### Connecting to In-Memory DuckDB (Dev Mode) ```json { "mcpServers": { "DuckDB (in-memory, r/w)": { "command": "uvx", "args": ["mcp-server-motherduck", "--db-path", ":memory:", "--read-write", "--allow-switch-databases"] } } } ``` Full flexibility with no guardrails — read-write access and the ability to switch to any database (local files, S3, or MotherDuck) at runtime. ### Connecting to a Local DuckDB File in Read-Only Mode ```json { "mcpServers": { "DuckDB (read-only)": { "command": "uvx", "args": ["mcp-server-motherduck", "--db-path", "/absolute/path/to/your.duckdb"] } } } ``` Connects to a specific DuckDB file in read-only mode. Won't hold on to the file lock, so convenient to use alongside a write connection to the same DuckDB file. You can also connect to remote DuckDB files on S3 using `s3://bucket/path.duckdb` — see [Environment Variables](#environment-variables) for S3 authentication. If you're considering third-party access to the MCP, see [Securing for Production](#securing-for-production). ### Connecting to MotherDuck in Read-Write Mode ```json { "mcpServers": { "MotherDuck (local, r/w)": { "command": "uvx", "args": ["mcp-server-motherduck", "--db-path", "md:", "--read-write"], "env": { "motherduck_token": "" } } } } ``` See [Command Line Parameters](#command-line-parameters) for more options, [Securing for Production](#securing-for-production) for deployment guidance, and [Troubleshooting](#troubleshooting) if you encounter issues. ## Client Setup | Client | Config Location | One-Click Install | |--------|-----------------|-------------------| | **Claude Desktop** | Settings → Developer → Edit Config | [.mcpb (MCP Bundle)](https://github.com/motherduckdb/mcp-server-motherduck/releases/latest/download/mcp-server-motherduck.mcpb) | | **Claude Code** | Use CLI commands below | - | | **Codex CLI** | Use CLI commands below | - | | **Cursor** | Settings → MCP → Add new global MCP server | [Install in Cursor](https://cursor.com/en/install-mcp?name=DuckDB&config=eyJjb21tYW5kIjoidXZ4IG1jcC1zZXJ2ZXItbW90aGVyZHVjayAtLWRiLXBhdGggOm1lbW9yeTogLS1yZWFkLXdyaXRlIC0tYWxsb3ctc3dpdGNoLWRhdGFiYXNlcyIsImVudiI6e319) | | **VS Code** | `Ctrl+Shift+P` → "Preferences: Open User Settings (JSON)" | [![Install with UV in VS Code](https://img.shields.io/badge/VS_Code-Install-0098FF?style=flat-square)](https://insiders.vscode.dev/redirect/mcp/install?name=mcp-server-motherduck&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22mcp-server-motherduck%22%2C%22--db-path%22%2C%22%3Amemory%3A%22%2C%22--read-write%22%2C%22--allow-switch-databases%22%5D%7D) | Any MCP-compatible client can use this server. Add the JSON configuration from [Quick Start](#quick-start) to your client's MCP config file. Consult your client's documentation for the config file location.
Claude Code CLI commands **In-Memory DuckDB (Dev Mode):** ```bash claude mcp add --scope user duckdb --transport stdio -- uvx mcp-server-motherduck --db-path :memory: --read-write --allow-switch-databases ``` **Local DuckDB (Read-Only):** ```bash claude mcp add --scope user duckdb --transport stdio -- uvx mcp-server-motherduck --db-path /absolute/path/to/db.duckdb ``` **MotherDuck (Read-Write):** ```bash claude mcp add --scope user motherduck --transport stdio --env motherduck_token=YOUR_TOKEN -- uvx mcp-server-motherduck --db-path md: --read-write ```
Codex CLI commands **In-Memory DuckDB (Dev Mode):** ```bash codex mcp add duckdb -- uvx mcp-server-motherduck --db-path :memory: --read-write --allow-switch-databases ``` **Local DuckDB (Read-Only):** ```bash codex mcp add duckdb -- uvx mcp-server-motherduck --db-path /absolute/path/to/db.duckdb ``` **MotherDuck (Read-Write):** ```bash codex mcp add motherduck --env motherduck_token=YOUR_TOKEN -- uvx mcp-server-motherduck --db-path md: --read-write ```
## Tools | Tool | Description | Required Inputs | Optional Inputs | |------|-------------|-----------------|-----------------| | `execute_query` | Execute SQL query (DuckDB dialect) | `sql` | - | | `list_databases` | List all databases (useful for MotherDuck or multiple attached DBs) | - | - | | `list_tables` | List tables and views | - | `database`, `schema` | | `list_columns` | List columns of a table/view | `table` | `database`, `schema` | | `switch_database_connection`* | Switch to different database | `path` | `create_if_not_exists` | *Requires `--allow-switch-databases` flag All tools return JSON. Results are limited to 1024 rows / 50,000 chars by default (configurable via `--max-rows`, `--max-chars`). ## Securing for Production When giving third parties access to a self-hosted MCP server, **read-only mode alone is not sufficient** — it still allows access to the local filesystem, changing DuckDB settings, and other potentially sensitive operations. For production deployments with third-party access, we recommend **[MotherDuck Remote MCP](https://motherduck.com/docs/sql-reference/mcp/)** — zero-setup, read-write capable, and hosted by MotherDuck. **Self-hosting MotherDuck MCP:** Fork this repo and customize as needed. Use a **[service account](https://motherduck.com/docs/key-tasks/service-accounts-guide/)** with **[read-scaling tokens](https://motherduck.com/docs/key-tasks/authenticating-and-connecting-to-motherduck/read-scaling/#creating-a-read-scaling-token)** and enable **[SaaS mode](https://motherduck.com/docs/key-tasks/authenticating-and-connecting-to-motherduck/authenticating-to-motherduck/#authentication-using-saas-mode)** to restrict local file access. **Self-hosting DuckDB MCP:** Use `--init-sql` to apply security settings. See the [Securing DuckDB guide](https://duckdb.org/docs/stable/operations_manual/securing_duckdb/overview) for available options. ## Command Line Parameters | Parameter | Default | Description | |-----------|---------|-------------| | `--db-path` | `:memory:` | Database path: local file (absolute), `md:` (MotherDuck), or `s3://` URL | | `--motherduck-token` | `motherduck_token` env var | MotherDuck access token | | `--read-write` | `False` | Enable write access | | `--motherduck-saas-mode` | `False` | MotherDuck SaaS mode (restricts local access) | | `--allow-switch-databases` | `False` | Enable `switch_database_connection` tool | | `--max-rows` | `1024` | Max rows returned | | `--max-chars` | `50000` | Max characters returned | | `--query-timeout` | `-1` | Query timeout in seconds (-1 = disabled) | | `--init-sql` | `None` | SQL to execute on startup | | `--motherduck-connection-parameters` | `session_hint=mcp&`
`dbinstance_inactivity_ttl=0s` | Additional MotherDuck connection string parameters (`key=value` pairs separated by `&`) | | `--ephemeral-connections` | `True` | Use temporary connections for read-only local files | | `--transport` | `stdio` | Transport type: `stdio` or `http` | | `--stateless-http` | `False` | For protocol compatibility only (e.g. with [AWS Bedrock AgentCore Runtime](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-mcp-protocol-contract.html)). Server still maintains global state via the shared DatabaseClient. | | `--port` | `8000` | Port for HTTP transport | | `--host` | `127.0.0.1` | Host for HTTP transport | ## Environment Variables | Variable | Description | |----------|-------------| | `motherduck_token` or `MOTHERDUCK_TOKEN` | MotherDuck access token (alternative to `--motherduck-token`) | | `HOME` | Used by DuckDB for extensions and config. Override with `--home-dir` if not set. | | `AWS_ACCESS_KEY_ID` | AWS access key for S3 database connections | | `AWS_SECRET_ACCESS_KEY` | AWS secret key for S3 database connections | | `AWS_SESSION_TOKEN` | AWS session token for temporary credentials (IAM roles, SSO, EC2 instance profiles) | | `AWS_D ---