mcp-server-duckdb
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| db-path | Yes | Path to the DuckDB database file. The server will automatically create the database file and parent directories if they don't exist. | |
| readonly | No | Run server in read-only mode. When set to 'true', the DuckDB database is opened with read_only=True, preventing any write operations. If the specified database file does not exist, the server will fail to start. | false |
| keep-connection | No | Re-uses a single DuckDB connection for the entire server lifetime. Enables TEMP objects and slightly faster queries, but can hold an exclusive lock on the file. | false |
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 |
|---|---|
| queryC | Execute a query on the DuckDB database |
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 1 tool
With only one tool, there is no possibility of confusion between tools. The 'query' tool has a single, unambiguous purpose of executing DuckDB queries.
The single tool name 'query' is a clear, straightforward verb that accurately describes its function. With only one tool, naming consistency is trivially satisfied.
One tool is on the thin side for a full database server like DuckDB. While a generic query tool can cover many operations, it lacks typical helper tools (e.g., schema listing, table inspection) that agents might expect, making the count borderline.
The query tool can execute any SQL, enabling full CRUD and DDL operations, so there are no direct dead ends. However, there is no built-in schema discovery or validation, which is a minor gap that agents can work around via SQL queries against system tables.