広告掲載
MCP.so
ログイン

MCP Host CLI

@VyacheslavVanin

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

VyacheslavVanin

MCP Host CLI について

Local http server that proxies requests o LLMs and uses mcp-servers if needed

MCP Host CLI の設定

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": {
    "mcp-http-host": {
      "command": "uv",
      "args": [
        "run",
        "main.py"
      ]
    }
  }
}

MCP Host CLI のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is MCP Host CLI?

It is a FastAPI server for chat interactions with LLMs, using OpenAI-compatible providers. It is configured via environment variables and CLI arguments, and supports tool approval workflows.

How to use MCP Host CLI?

Configure via environment variables (e.g., LLM_API_KEY, LLM_MODEL) or CLI arguments (e.g., --model, --port). Start the server using uv run main.py with desired options. Send requests to endpoints like POST /user_request and POST /approve.

Key features of MCP Host CLI

  • FastAPI server for chat interactions with LLMs
  • Configurable via environment variables and CLI arguments
  • Supports OpenAI-compatible providers (e.g., OpenRouter)
  • Tool approval workflow with request/response endpoints
  • Streaming mode and retry on LLM errors

Use cases of MCP Host CLI

  • Building a backend for chat interfaces with LLMs
  • Integrating LLM chat with tool approval mechanisms
  • Running a local or remote LLM chat server with OpenAI-compatible API

よくある質問

1

How do I configure the LLM model?

Use the `LLM_MODEL` environment variable or the `--model` CLI argument. Default is `qwen2.5-coder:latest`.

2

How do I provide the API key?

Set the `LLM_API_KEY` environment variable or use the `--api-key-file` CLI argument pointing to a file with the key.

3

What LLM providers are supported?

Only `openai` provider is supported, but the base URL can be changed (default OpenRouter).

4

How do I approve a tool call?

Send a POST request to `/approve` with `request_id` and `approve` boolean in the JSON body.

5

Where are debug messages logged?

If `--debug-messages` is enabled, logs are written to `/tmp/llm-requester.messages.log`.

コメント

「開発者ツール」の他のコンテンツ

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

12

Meticulous

Meticulous

Collide MCP

Lithometric Inc. | Collide Inc.

Collide is the multiplayer layer for AI coding agents, and it pays for itself. Expert orchestration across every agent on your repo saves teams tens to hundreds of dollars a day in token burn. Run Claude Code, Codex, Cu

Perfex CRM

themesic

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

1

Windframe

Windframe MCP gives your AI the design taste needed to create consistent, production-ready UI that feels intentionally designed. Available at https://windframe.dev/mcp

広告掲載