mcp-clickhouse-long-running
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_databasesB | List available ClickHouse databases |
| list_tablesC | List available ClickHouse tables in a database, including schema, comment, row count, and column count. |
| run_select_queryC | Run a SELECT query in a ClickHouse 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 3 tools
Each tool has a clearly distinct purpose: list_databases for database enumeration, list_tables for table metadata within a database, and run_select_query for executing queries. There is no overlap in functionality, making tool selection straightforward for an agent.
All tools follow a consistent verb_noun naming pattern (list_databases, list_tables, run_select_query), using snake_case throughout. This predictability aids in understanding and usage without any deviations.
With only 3 tools, the server feels thin for a database interaction scope, lacking operations like data manipulation (INSERT/UPDATE/DELETE), schema modification, or query execution beyond SELECT. While core functions are present, the count is borderline low for comprehensive database management.
The tool set is significantly incomplete for ClickHouse database operations, covering only listing and SELECT queries. Missing are essential CRUD operations (e.g., INSERT, UPDATE, DELETE), schema changes (CREATE/ALTER/DROP), and other query types (e.g., SHOW, DESCRIBE), which will likely cause agent failures in broader workflows.