Skip to main content
Glama
enesjakozh
burakdirin

clickhouse-mcp-server

by burakdirin
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Servidor MCP de Clickhouse

insignia de herrería

Un proyecto de servidor MCP de base de datos de Clickhouse.

Instalación

Puedes instalar el paquete usando uv :

uv pip install clickhouse-mcp-server

O usando pip :

pip install clickhouse-mcp-server

Related MCP server: ClickHouse MCP Server

Componentes

Herramientas

El servidor proporciona dos herramientas:

  • connect_database : se conecta a una base de datos específica de Clickhouse

    • parámetro database : Nombre de la base de datos a la que conectarse (cadena)

    • Devuelve un mensaje de confirmación cuando la conexión es exitosa

  • execute_query : ejecuta consultas de Clickhouse

    • parámetro query : consulta/consultas SQL a ejecutar (cadena)

    • Devuelve los resultados de la consulta en formato JSON

    • Se pueden enviar múltiples consultas separadas por punto y coma

Configuración

El servidor utiliza las siguientes variables de entorno:

  • CLICKHOUSE_HOST : Dirección del servidor de Clickhouse (predeterminado: "localhost")

  • CLICKHOUSE_USER : Nombre de usuario de Clickhouse (predeterminado: "root")

  • CLICKHOUSE_PASSWORD : Contraseña de Clickhouse (predeterminada: "")

  • CLICKHOUSE_DATABASE : Base de datos inicial (opcional)

  • CLICKHOUSE_READONLY : modo de solo lectura (establecido en 1/verdadero para habilitar, predeterminado: falso)

Inicio rápido

Instalación

Escritorio de Claude

MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json

Ventanas: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "clickhouse-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/burakdirin/Projects/clickhouse-mcp-server",
        "run",
        "clickhouse-mcp-server"
      ],
      "env": {
        "CLICKHOUSE_HOST": "localhost",
        "CLICKHOUSE_USER": "root",
        "CLICKHOUSE_PASSWORD": "password",
        "CLICKHOUSE_DATABASE": "[optional]",
        "CLICKHOUSE_READONLY": "true"
      }
    }
  }
}
{
  "mcpServers": {
    "clickhouse-mcp-server": {
      "command": "uvx",
      "args": [
        "clickhouse-mcp-server"
      ],
      "env": {
        "CLICKHOUSE_HOST": "localhost",
        "CLICKHOUSE_USER": "root",
        "CLICKHOUSE_PASSWORD": "password",
        "CLICKHOUSE_DATABASE": "[optional]",
        "CLICKHOUSE_READONLY": "true"
      }
    }
  }
}

Instalación mediante herrería

Para instalar automáticamente Clickhouse Database Integration Server para Claude Desktop a través de Smithery :

npx -y @smithery/cli install @burakdirin/clickhouse-mcp-server --client claude

Desarrollo

Construcción y publicación

Para preparar el paquete para su distribución:

  1. Sincronizar dependencias y actualizar archivo de bloqueo:

uv sync

  1. Distribuciones de paquetes de compilación:

uv build

Esto creará distribuciones de origen y de rueda en el directorio dist/ .

  1. Publicar en PyPI:

uv publish

Nota: Deberás configurar las credenciales de PyPI a través de variables de entorno o indicadores de comando:

  • Token: --token o UV_PUBLISH_TOKEN

  • O nombre de usuario/contraseña: --username / UV_PUBLISH_USERNAME y --password / UV_PUBLISH_PASSWORD

Depuración

Dado que los servidores MCP se ejecutan en stdio, la depuración puede ser complicada. Para una experiencia óptima, recomendamos usar el Inspector MCP .

Puede iniciar el Inspector MCP a través de npm con este comando:

npx @modelcontextprotocol/inspector uv --directory /Users/burakdirin/Projects/clickhouse-mcp-server run clickhouse-mcp-server

Al iniciarse, el Inspector mostrará una URL a la que podrá acceder en su navegador para comenzar a depurar.

Available Tools

2 tools
connect_databaseC

Connect to a specific ClickHouse database

ParametersJSON Schema
NameRequiredDescriptionDefault
databaseYes

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It only says 'Connect', omitting details about side effects, authentication requirements, or state changes (e.g., establishing a session).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no unnecessary words. It is effectively concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's role as a connection setter, the description lacks information on prerequisites, return values, or how it interacts with 'execute_query'. It is incomplete for operational context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the description adds no additional meaning beyond the parameter name 'database'. It does not explain valid values or expected format.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Connect to a specific ClickHouse database', using a specific verb and resource. It effectively distinguishes from the sibling tool 'execute_query' which presumably runs queries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus the sibling 'execute_query' or any prerequisites. The description merely states functionality without usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

execute_queryC

Execute ClickHouse queries

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes

TDQS

C2.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided. The description does not disclose whether queries are read-only, safe, or have side effects. Important behavioral details like result handling or error behavior are missing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise but at the expense of necessary detail for a query execution tool. It is too minimal to be considered well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With one parameter and no output schema, the description fails to explain what the tool returns or if it just executes. Lacks context about execution environment and limitations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, and the description adds no information about the 'query' parameter beyond its name. Does not specify expected format (e.g., SQL dialect) or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (Execute) and resource (ClickHouse queries). It distinguishes from the sibling tool connect_database, which implies connection setup vs query execution.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. Does not mention prerequisites like a prior connection or whether it is for read or write operations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.0.0
    • First observedconnect_database
    • First observedexecute_query
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.1/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one for establishing a database connection, the other for executing queries. There is no overlap or ambiguity.

Naming Consistency5/5

Both tool names follow a consistent verb_noun pattern (connect_database, execute_query), making them predictable and easy to understand.

Tool Count4/5

With only 2 tools, the set is minimal but still covers the essential operations for a database query server. It is slightly thin but reasonable for a focused scope.

Completeness3/5

The tools cover connection and query execution, but lack disconnect, schema inspection, or database management operations. This leaves notable gaps for a full database interaction workflow.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

  • ClickHouse MCP Server

    ThomAub
    A
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that enables Large Language Models to seamlessly interact with ClickHouse databases, supporting resource listing, schema retrieval, and query execution.
    2
    MIT

  • MariaDB MCP Server

    abel9851
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server implementation that enables Claude to execute read-only queries against MariaDB databases and explore database schemas through natural language.
    20
    MIT
  • Altinity MCP by Altinity

    Altinity MCPofficial

    Altinity
    F
    license
    Not graded
    quality
    A
    maintenance
    Production-ready MCP server designed to empower AI agents and LLMs to interact seamlessly with ClickHouse. It exposes your ClickHouse database as a set of standardized tools and resources that adhere to the MCP protocol, making it easy for agents built on OpenAI, Claude, or other platforms to query, explore, and analyse your data.
    37
    -

Appeared in Searches