mcp-server-motherduck
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOME | No | Your home folder path (needed by DuckDB) | |
| motherduck_token | No | Your MotherDuck access token for authenticating to MotherDuck |
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| execute_queryA | Execute a SQL query on the DuckDB or MotherDuck database. Unqualified table names resolve to current_database() and current_schema() automatically. Fully qualified names (database.schema.table) are only needed when multiple DuckDB databases are attached or when connected to MotherDuck. |
| list_databasesA | List all databases available in the connection. Useful when multiple DuckDB databases are attached or when connected to MotherDuck. |
| list_tablesB | List all tables and views in a database with their comments. If database is not specified, uses the current database. |
| list_columnsA | List all columns of a table or view with their types and comments. If database/schema are not specified, uses the current database/schema. |
| switch_database_connectionA | Switch to a different database connection. For local files, use absolute paths only. The new connection respects the server's read-only/read-write mode. For local files, the file must exist unless create_if_not_exists=True (requires read-write mode). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: execute_query runs SQL, list_databases/tables/columns return metadata, switch_database_connection manages connections. Overlap is minimal because the listing tools target different entity levels (databases, tables, columns).
All tools use a consistent verb_noun snake_case pattern: execute_query, list_databases, list_tables, list_columns, switch_database_connection. The naming is predictable and readable.
Five tools is well-scoped for a database interface: one query executor, three metadata listers, and one connection switcher. No obvious missing core operations given the server's purpose.
The surface covers querying, schema exploration, and connection management. However, it lacks tools for database writing/DDL (e.g., create table, insert) or connection closing, which might be needed for full lifecycle management.