clickhouse-mcp
A read-only MCP server for ClickHouse that enables AI agents to discover schema, sample data, and run read-only SQL queries to investigate observability data like logs, metrics, and traces.
README
clickhouse-mcp
A read-only Model Context Protocol server for ClickHouse. It gives an AI agent a small set of tools to explore a ClickHouse instance and investigate observability data (logs, metrics, traces) without being able to write or mutate anything.
Built as a reference for wiring agents onto a petabyte-scale analytics platform: the agent discovers the schema, samples data, and runs guarded read-only SQL to answer questions like "why did p99 latency spike at 02:14?".
Tools
| Tool | What it does |
|---|---|
list_databases |
SHOW DATABASES |
list_tables |
SHOW TABLES FROM <db> |
describe_table |
DESCRIBE TABLE <db>.<table> |
show_create_table |
SHOW CREATE TABLE (schema + engine + settings) |
sample_rows |
SELECT * FROM <db>.<table> LIMIT n (peek at the shape) |
query |
Arbitrary read-only SQL (SELECT/WITH/SHOW/DESCRIBE/EXPLAIN) |
Safety
- Verb guard: only
SELECT / WITH / SHOW / DESCRIBE / EXPLAIN / EXISTSare allowed; write/DDL verbs (INSERT,CREATE,DROP,ALTER,TRUNCATE, …) are rejected. - Limits: every query sets
max_result_rowsandmax_execution_time, and the rows returned to the model are capped (with a truncation note) to protect its context window. - Defence in depth: still point this at a read-only ClickHouse user. The app-level guard is a first line, not the only one.
Prerequisites
-
Node.js 20+
-
Any ClickHouse instance. Easiest is local docker (no setup, includes
system.*observability tables to play with):docker run -d --name ch -p 8123:8123 -p 9000:9000 clickhouse/clickhouse-server
Install
git clone <your-fork-url> clickhouse-mcp && cd clickhouse-mcp
npm install
cp .env.example .env # then edit if your ClickHouse needs auth
Verify it talks to ClickHouse
npm run self-test
# Connecting to http://localhost:8123
# databases: [ 'default', 'system', 'INFORMATION_SCHEMA', ... ]
# version: [ { v: '25.x.x.x' } ]
# OK
Run as an MCP server (stdio)
npm start
Use it from a client
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"clickhouse": {
"command": "npx",
"args": ["tsx", "/absolute/path/to/clickhouse-mcp/src/index.ts"],
"env": {
"CLICKHOUSE_URL": "http://localhost:8123",
"CLICKHOUSE_USERNAME": "default",
"CLICKHOUSE_PASSWORD": ""
}
}
}
}
Claude Code:
claude mcp add clickhouse -e CLICKHOUSE_URL=http://localhost:8123 -- npx tsx /absolute/path/to/clickhouse-mcp/src/index.ts
MCP Inspector (great for debugging the tools directly):
npx @modelcontextprotocol/inspector npx tsx src/index.ts
Then ask an agent: "What tables are in the system database? Show recent slow queries from system.query_log grouped by minute."
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。