Codehooks.io MCP Server (under construction 🚧)
@RestDB
Codehooks.io MCP Server (under construction 🚧) について
MCP server for codehooks.io
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"codehooks-mcp-server": {
"command": "docker",
"args": [
"run",
"-d",
"\\"
]
}
}
}ツール
2collection (required), query (optional), limit (optional)
filename (required), code (required)
概要
What is Codehooks.io MCP Server?
The Codehooks.io MCP Server is a Model Context Protocol server that gives AI agents like Claude direct tools to interact with Codehooks.io projects. It authenticates via an admin token and runs as a Docker container, enabling operations such as querying collections and deploying JavaScript code.
How to use Codehooks.io MCP Server?
Run the Docker container with the required environment variables (CODEHOOKS_PROJECT_NAME, CODEHOOKS_SPACE, CODEHOOKS_ADMIN_TOKEN). Obtain your admin token using the Codehooks CLI commands coho login and coho add-admintoken. Configure the server for Claude Desktop or Cursor by adding the Docker command to their respective MCP settings files.
Key features of Codehooks.io MCP Server
- Runs as a lightweight Docker container
- Authenticates using a Codehooks.io admin token
- Supports querying collections with optional query and limit
- Provides a deploy_code tool (currently non‑functional)
- Works with Claude Desktop and Cursor
- Testable via JSON‑RPC requests over stdio
Use cases of Codehooks.io MCP Server
- AI agents querying data from Codehooks.io collections
- Automated retrieval of project data during AI conversations
- Exploring and debugging Codehooks.io projects through natural language
FAQ from Codehooks.io MCP Server
What does this server do?
It exposes Codehooks.io project operations as tools for AI agents, allowing them to query collections and (soon) deploy code without manual API calls.
How do I get an admin token for authentication?
Run coho login in your terminal, follow the login prompt, then execute coho add-admintoken and copy the returned token.
What environment variables are required?
You must set CODEHOOKS_PROJECT_NAME, CODEHOOKS_SPACE (e.g., "dev" or "prod"), and CODEHOOKS_ADMIN_TOKEN. The MCP server uses the admin token directly, so no additional login is needed.
How can I verify the server is working?
Run the Docker container interactively, send a list_tools JSON‑RPC request, and expect a proper JSON response listing tools like query_collection and deploy_code.
Are there any tools that are not yet functional?
Yes, the deploy_code tool is explicitly marked as “NOT WORKING YET!”. The query_collection tool is fully operational.
「その他」の他のコンテンツ
🪟 Windows-MCP
CursorTouchMCP Server for Computer Use in Windows
Core Philosophy: Connect, Unify, Respond
mindsdbDelegate anything. It comes back done.
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
Inbox Zero AI
elie222The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
コメント