● 社群 julien040 ⚡ 即開即用

Anyquery

Name: Anyquery MCP Server
Author: julien040

Query 40+ apps (GitHub, Notion, Slack, ...) with SQL via MCP.

Anyquery is a SQL query engine that talks to 40+ SaaS apps (GitHub, Notion, Slack, Airtable, Linear) and local files (CSV, JSON, Parquet). Through MCP it exposes those tables to Claude, so an LLM can ask cross-source questions in plain SQL without writing per-API glue.

▶ 觀看演示 📦 安裝 💡 使用場景

為什麼要用

核心特性

40+ pre-built data sources covering GitHub, Notion, Linear, Airtable, Slack, calendar, Spotify
Local file query (CSV, Parquet, JSON, log files) via SQLite virtual tables
Single binary, single MCP endpoint — Claude sees one SQL schema across all sources
Pluggable connector architecture — write your own with a small Go/TS plugin
Compatible with the MySQL wire protocol for ad-hoc psql-style use

即時演示

實際使用效果

anyquery-mcp.replay ▶ 就緒

0/0

安裝

選擇你的客戶端

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "anyquery-mcp": {
      "command": "anyquery",
      "args": [
        "mcp"
      ]
    }
  }
}

開啟 Claude Desktop → Settings → Developer → Edit Config。儲存後重啟應用。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "anyquery-mcp": {
      "command": "anyquery",
      "args": [
        "mcp"
      ]
    }
  }
}

Cursor 使用與 Claude Desktop 相同的 mcpServers 格式。專案級設定優先於全域。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "anyquery-mcp": {
      "command": "anyquery",
      "args": [
        "mcp"
      ]
    }
  }
}

點擊 Cline 側欄中的 MCP Servers 圖示，然後選 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "anyquery-mcp": {
      "command": "anyquery",
      "args": [
        "mcp"
      ]
    }
  }
}

格式與 Claude Desktop 相同。重啟 Windsurf 生效。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "anyquery-mcp",
      "command": "anyquery",
      "args": [
        "mcp"
      ]
    }
  ]
}

Continue 使用伺服器物件陣列，而非映射。

~/.config/zed/settings.json

{
  "context_servers": {
    "anyquery-mcp": {
      "command": {
        "path": "anyquery",
        "args": [
          "mcp"
        ]
      }
    }
  }
}

加入 context_servers。Zed 儲存後熱重載。

claude mcp add anyquery-mcp -- anyquery mcp

一行命令搞定。用 claude mcp list 驗證，claude mcp remove 移除。

使用場景

實戰用法： Anyquery

Generate a weekly status report joining GitHub PRs and Linear tickets

👤 Engineering leads ⏱ ~15 min intermediate

何時使用： You want one summary across multiple SaaS tools without writing API code.

前置條件

Server/skill installed and authenticated — See repo README

步驟

List the connected tables

Show me every table anyquery has, grouped by source app.✓ 已複製

→ Tables grouped by github/linear/slack/...
Write the join

For PRs merged this week in org acme/, find the matching Linear ticket by branch name and tell me which tickets shipped.✓ 已複製

→ A SQL JOIN between github_pulls and linear_issues with shipped tickets

結果： A one-shot status digest you can paste into Slack.

注意事項

Tables only have data for connected accounts — Tables only have data for connected accounts — run anyquery plugin install <name> and authenticate before querying.

搭配使用： github · linear · notion

組合

與其他 MCP 搭配，撬動十倍槓桿

anyquery-mcp + github

Pair with github for complementary capabilities

Use this server together with github to complete a multi-step task.✓ 已複製

anyquery-mcp + linear

Pair with linear for complementary capabilities

Use this server together with linear to complete a multi-step task.✓ 已複製

工具

此 MCP 暴露的能力

工具	輸入參數	何時呼叫	成本
list_tables	(none)	Discover which app/file tables are available before querying	free
describe_table	name: str	Inspect columns of a specific table	free
execute_query	sql: str	Run a SELECT across one or more sources	Underlying SaaS API quota

成本與限制

運行它的成本

API 配額: See provider docs for rate limits
每次呼叫 Token 數: Varies by tool
費用: See repo README for pricing details
提示: Cache tool results and avoid repeated identical calls.

安全

權限、密鑰、影響範圍

憑證儲存： Use environment variables; never commit secrets

資料出站： Tool calls go to the provider's API as documented

故障排查

常見錯誤與修復

table 'github_pulls' does not exist

Install and authenticate the GitHub plugin: anyquery plugin install github && anyquery plugin login github

驗證： Run list_tables and confirm github_pulls is present

rate limited by upstream API

Anyquery passes through the source's rate limit — add LIMIT and avoid SELECT * across millions of rows

驗證： Try a small LIMIT 10 query

替代方案

Anyquery 對比其他方案

替代方案	何時用它替代	權衡
MindsDB	You want federated ML/analytics, not just SQL access	Heavier — full DB platform vs single binary

資源

📖 閱讀 GitHub 上的官方 README

🐙 查看未解決的 issue

🔍 瀏覽全部 400+ MCP 伺服器和 Skills