MotherDuck DuckDB MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| motherduck_token | No | Access token for MotherDuck. Used as default for --motherduck-token if not provided. | |
| AWS_ACCESS_KEY_ID | No | AWS access key ID for S3 connections. | |
| AWS_SESSION_TOKEN | No | AWS session token for temporary credentials (SSO). | |
| AWS_DEFAULT_REGION | No | AWS default region for S3 connections. | |
| AWS_SECRET_ACCESS_KEY | No | AWS secret access key for S3 connections. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| queryA | Use this to execute a query on the MotherDuck or DuckDB database |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| duckdb-motherduck-initial-prompt | A prompt to initialize a connection to duckdb or motherduck and start working with it |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion or overlap. The tool's purpose is clear.
The single tool name 'query' is a simple, imperative verb that clearly describes its action. No mixed conventions to judge.
With only one tool, the server feels thin for a general-purpose database server, though it can technically execute any SQL. It falls in the borderline range for a small server.
The tool allows arbitrary query execution, which can cover metadata via system tables, but lacks dedicated tools for listing tables or schemas, requiring agents to know SQL to explore the database.