ClickHouse MCP Server
Databasestdiov0.4.0
Provides AI agents with access to ClickHouse analytical databases through the Model Context Protocol. Enables running analytical queries, exploring table schemas, inspecting materialized views, and monitoring query performance. Designed for OLAP workloads with support for large result sets and query profiling.
Connect
Add this configuration to .claude/mcp.json
{
"mcpServers": {
"clickhouse": {
"command": "npx",
"args": [
"-y",
"@clickhouse/mcp-server"
],
"env": {
"CLICKHOUSE_HOST": "<YOUR_CLICKHOUSE_HOST>",
"CLICKHOUSE_PORT": "<YOUR_CLICKHOUSE_PORT>",
"CLICKHOUSE_USER": "<YOUR_CLICKHOUSE_USER>",
"CLICKHOUSE_PASSWORD": "<YOUR_CLICKHOUSE_PASSWORD>"
}
}
}
}Tools (4)
run_query
Execute a ClickHouse SQL query and return results. Supports SELECT, SHOW, DESCRIBE, and EXPLAIN statements.
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "ClickHouse SQL query to execute"
},
"format": {
"type": "string",
"description": "Output format (JSON, TabSeparated, CSV, Pretty)"
},
"max_rows": {
"type": "integer",
"description": "Maximum rows to return"
}
}
}list_databases
List all databases in the ClickHouse instance.
{
"type": "object",
"properties": {}
}describe_table
Show the schema of a ClickHouse table including column types, codecs, and TTL rules.
{
"type": "object",
"required": [
"database",
"table"
],
"properties": {
"table": {
"type": "string",
"description": "Table name"
},
"database": {
"type": "string",
"description": "Database name"
}
}
}query_profile
Analyze query execution plan and performance metrics for optimization.
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "Query to analyze"
}
}
}Resources
This server does not expose any resources.
Prompts
This server does not expose any prompts.
Server Information
- Author
- ClickHouse (@ClickHouse)
- License
- Apache-2.0
- Version
- 0.4.0
- Stars
- 1,560
- Last Updated
- May 15, 2026