Mcp Server Motherduck

io.github.motherduckdbPublished by GitHub account motherduckdbv1.1.0Updated Oct 24, 2026

SQL analytics and data engineering for AI Assistants and IDEs

VerifiedSTDIODesktop onlyDatabasesData & Analytics

Overview

AI-generated overview

Local MCP server that connects an AI assistant to DuckDB and MotherDuck so it can run analytical SQL, browse catalogs and switch databases.

What you can do
Run SQL queries against DuckDB or MotherDuck, including read and write statements when enabled, with results returned as JSON and capped by row and character limits by default. Browse database catalogs by listing databases, tables and views, and columns of a table or view. Switch the active database connection to another local file, S3 path or MotherDuck database when the switch flag is enabled. Query across local and remote databases and ingest or export data through the local filesystem.
When to use it
Use it when an assistant should analyze data with DuckDB's SQL engine, work with local DuckDB files, in-memory databases or MotherDuck, or run data engineering queries from an IDE or chat client. It is the local option; a hosted MotherDuck remote server exists for zero-setup use.
Requirements
Runs locally as a Python package launched with uvx, so uv must be installed. A database path is chosen with a flag: in-memory, an absolute local file, an s3:// URL or md: for MotherDuck. MotherDuck needs a token via the motherduck_token or MOTHERDUCK_TOKEN variable or the token flag; S3 access needs AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY and optionally AWS_SESSION_TOKEN, AWS_DEFAULT_REGION and AWS_ENDPOINT. HOME is used by DuckDB for extensions and config.
Before you install
Write access is off by default and enabled with a read-write flag; the in-memory dev configuration is described as having no guardrails, with read-write access and switching to any database at runtime. The README warns that read-only mode alone is not sufficient when giving third parties access, since it still allows local filesystem access and changing DuckDB settings. MotherDuck tokens and AWS credentials are secrets passed by environment variable or flag.

Installation

In SourceWeft

  1. Open Mcp Server Motherduck in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

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

Remote vs Local MCP

Remote MCPLocal MCP (this repo)
HostingHosted by MotherDuckRuns locally/self-hosted
SetupZero-setupRequires local installation
AccessRead-write supportedRead-write supported
Local filesystem-Query across local and remote databases, ingest data from / export data to local filesystem

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 for S3 authentication. If you're considering third-party access to the MCP, see 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": "<YOUR_MOTHERDUCK_TOKEN>"      }    }  }}

See Command Line Parameters for more options, Securing for Production for deployment guidance, and Troubleshooting if you encounter issues.

Client Setup

ClientConfig LocationOne-Click Install
Claude DesktopSettings → Developer → Edit Config.mcpb (MCP Bundle)
Claude CodeUse CLI commands below-
Codex CLIUse CLI commands below or ~/.codex/config.toml-
Gemini CLIUse CLI commands below or ~/.gemini/settings.json-
CursorSettings → MCP → Add new global MCP server[Install in Cursor]
VS CodeCtrl+Shift+P → "Preferences: Open User Settings (JSON)"[Install with UV in VS Code]
Kiro~/.kiro/settings/mcp.json (global) or .kiro/settings/mcp.json (project)[Add to Kiro]

Any MCP-compatible client can use this server. Add the JSON configuration from 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
Gemini CLI commands

In-Memory DuckDB (Dev Mode):

bash
gemini mcp add -s user duckdb uvx mcp-server-motherduck --db-path :memory: --read-write --allow-switch-databases

Local DuckDB (Read-Only):

bash
gemini mcp add -s user duckdb uvx mcp-server-motherduck --db-path /absolute/path/to/db.duckdb

MotherDuck (Read-Write):

bash
gemini mcp add -s user -e motherduck_token=YOUR_TOKEN motherduck uvx mcp-server-motherduck --db-path md: --read-write
Kiro manual JSON config

Add the following to your Kiro MCP config file (~/.kiro/settings/mcp.json for global, or .kiro/settings/mcp.json for project-scoped). See the Kiro MCP documentation for more details.

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"]    }  }}

MotherDuck (Read-Write):

json
{  "mcpServers": {    "MotherDuck (local, r/w)": {      "command": "uvx",      "args": ["mcp-server-motherduck", "--db-path", "md:", "--read-write"],      "env": {        "motherduck_token": "<YOUR_MOTHERDUCK_TOKEN>"      }    }  }}

Tools

ToolDescriptionRequired InputsOptional Inputs
execute_queryExecute SQL query (DuckDB dialect)sql-
list_databasesList all databases (useful for MotherDuck or multiple attached DBs)--
list_tablesList tables and views-database, schema
list_columnsList columns of a table/viewtabledatabase, schema
switch_database_connection*Switch to different databasepathcreate_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 — zero-setup, read-write capable, and hosted by MotherDuck.

Self-hosting MotherDuck MCP: Fork this repo and customize as needed. Use a service account with read-scaling tokens and enable SaaS mode to restrict local file access.

Self-hosting DuckDB MCP: Use --init-sql to apply security settings. See the Securing DuckDB guide for available options.

Docker

Build and run the server with Streamable HTTP on port 8000 (defaults to an in-memory DuckDB):

bash
docker build -t mcp-server-motherduck .docker run --rm -p 8000:8000 mcp-server-motherduck

Connect to MotherDuck by passing a token and overriding the command:

bash
docker run --rm -p 8000:8000 \  -e motherduck_token="$MOTHERDUCK_TOKEN" \  mcp-server-motherduck --transport http --db-path md:

The MCP endpoint is available at http://localhost:8000/mcp. CLI flags and env vars from below still apply.

Command Line Parameters

ParameterDefaultDescription
--db-path:memory:Database path: local file (absolute), md: (MotherDuck), or s3:// URL
--motherduck-tokenmotherduck_token env varMotherDuck access token
--read-writeFalseEnable write access
--motherduck-saas-modeFalseMotherDuck SaaS mode (restricts local access)
--allow-switch-databasesFalseEnable switch_database_connection tool
--max-rows1024Max rows returned
--max-chars50000Max characters returned
--query-timeout-1Query timeout in seconds (-1 = disabled)
--init-sqlNoneSQL to execute on startup
--motherduck-connection-parameterssession_hint=mcp&
dbinstance_inactivity_ttl=0s
Additional MotherDuck connection string parameters (key=value pairs separated by &)
--ephemeral-connectionsTrueUse temporary connections for read-only local files
--transportstdioTransport type: stdio or http
--stateless-httpFalseFor protocol compatibility only (e.g. with AWS Bedrock AgentCore Runtime). Server still maintains global state via the shared DatabaseClient.
--port8000Port for HTTP transport
--host127.0.0.1Host for HTTP transport

Environment Variables

VariableDescription
motherduck_token or MOTHERDUCK_TOKENMotherDuck access token (alternative to --motherduck-token)
HOMEUsed by DuckDB for extensions and config. Override with --home-dir if not set.
AWS_ACCESS_KEY_IDAWS access key for S3 database connections
AWS_SECRET_ACCESS_KEYAWS secret key for S3 database connections
AWS_SESSION_TOKENAWS session token for temporary credentials (IAM roles, SSO, EC2 instance profiles)
AWS_DEFAULT_REGIONAWS region for S3 connections
AWS_ENDPOINTAWS endpoint for S3 connections

Troubleshooting

  • spawn uvx ENOENT: Specify full path to uvx (run which uvx to find it)
  • File locked: Make sure --ephemeral-connections is turned on (default: true) and that you're not connected in read-write mode

Resources

Development

To run from source:

json
{  "mcpServers": {    "Local DuckDB (Dev)": {      "command": "uv",      "args": ["--directory", "/path/to/mcp-server-motherduck", "run", "mcp-server-motherduck", "--db-path", "md:"],      "env": {        "motherduck_token": "<YOUR_MOTHERDUCK_TOKEN>"      }    }  }}

Release Process

  1. Run the Release New Version GitHub Action
  2. Enter version in MAJOR.MINOR.PATCH format
  3. The workflow bumps version, publishes to PyPI/MCP registry, and creates the GitHub release with MCPB package

License

MIT License - see LICENSE file.

mcp-name: io.github.motherduckdb/mcp-server-motherduck

Source: README.md at commit 41acb58

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

2
  1. v1.1.0LatestOct 7, 2026
  2. v1.0.8Sep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts