MCP Plus

A lightweight MCP server offering context analysis, task delegation, chatroom coordination, and to-do management.

python

GitHub Stars

python

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "david3u-mcp-plus": {
      "command": "/path/to/mcp_plus/venv/bin/python",
      "args": [
        "/path/to/mcp_plus/mcp_server.py"
      ],
      "env": {
        "MODEL_NAME": "google/gemini-2.5-flash-lite",
        "SUBAGENT_MODEL": "moonshotai/kimi-k2-thinking",
        "OPENROUTER_API_KEY": "your_api_key_here"
      }
    }
  }
}

MCP Plus is a lightweight MCP server that equips AI agents with purpose-built tools to understand codebases, delegate tasks, coordinate multiple agents, and manage project to-dos. It runs as a single FastMCP server and integrates with any MCP-compatible client, enabling you to analyze code, distribute work, and stay synchronized across your team.

How to use

To use MCP Plus, connect your MCP client to the local stdio server you run on your machine. You’ll interact with a compact set of tools that let you query codebases, delegate file operations, post and read chatroom messages, and manage to-do lists. Use the context_engine to get a structural and architectural view of a project, the subagent to automate simple file tasks, and the chatroom and todo tools to keep team members aligned and on schedule.

How to install

Prerequisites you need before starting are Python 3.8 or newer and an OpenRouter API key. You will run MCP Plus from the command line and/or configure your MCP client to point at the local MCP server.

Ensure Python 3.8+ is installed on your system.
Obtain an OpenRouter API key and set it in your environment.
Prepare the MCP Plus runtime using the provided stdio configuration snippet and start the server.
Run MCP Plus directly if you prefer a quick start.
Start the server using the following command.

./run_server.sh

Configuration and startup details

The MCP Plus server is configured as a local stdio server. The runtime command points to a Python interpreter inside a virtual environment, running the MCP server script. The environment provides the API key, the base model, and the subagent model.

{
  "mcpServers": {
    "mcp_plus": {
      "command": "/path/to/mcp_plus/venv/bin/python",
      "args": ["/path/to/mcp_plus/mcp_server.py"],
      "env": {
        "OPENROUTER_API_KEY": "your_api_key_here",
        "MODEL_NAME": "google/gemini-2.5-flash-lite",
        "SUBAGENT_MODEL": "moonshotai/kimi-k2-thinking"
      }
    }
  }
}

Available tools

context_engine

Ask natural language questions about any codebase. Returns comprehensive analysis including file trees, relevant code snippets, and architectural insights.

subagent

Delegates basic tasks to a smaller, faster LLM that can read/write files autonomously.

chatroom_send_message

Post a message to a project's chatroom.

chatroom_read_messages

Read recent messages from the chatroom.

todo_list

View all todos for a project.

todo_update

Add, complete, or remove todos.

Built by

VeilStrat

AI signals for GTM teams