Plan_A

Plan_A的初心和目标是构建一个懂业务，能行动，产出质量高，能够让大家出门玩耍Agent可以在家自动办公的自动化办公文档产品。基于FastAPI的后端和VUE前端的全栈项目，支持MCP服务、用户登录等功能。

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio wanquany-plan_a docker compose up -d \
  --env LOG_LEVEL="INFO" \
  --env API_V1_STR="/api/v1" \
  --env SECRET_KEY="your-secret-key" \
  --env POSTGRES_DB="plan_a" \
  --env POSTGRES_USER="postgres" \
  --env OPENAI_API_KEY="your-openai-key" \
  --env POSTGRES_PASSWORD="your_password"

How to use

Plan_A provides a full-stack automation and document processing platform built on a FastAPI backend with a Vue frontend. It includes user authentication (JWT-based), asynchronous PostgreSQL operations with Alembic migrations, an MCP (Model Context Protocol) integration, and tooling for dynamic document editing, multi-format support, and real-time chat. The MCP integration enables agents to orchestrate external services and tools through standardized context, enabling automated办公 workflows. To use it, start the Docker Compose deployment described in the README, then access the frontend at the configured URL and interact with the agent-enabled assistant to process documents, invoke tools, and manage tasks within your workspace.

How to install

Prerequisites:

Docker and Docker Compose installed on your machine
Access to a PostgreSQL-compatible database via Docker or local instance
Basic understanding of environment variable configuration

Step-by-step:

Clone the repository: git clone <repository-url> && cd Plan_A
Prepare environment variables:
- Copy and edit the example env file if provided, or create necessary variables: POSTGRES_USER=postgres POSTGRES_PASSWORD=your_password POSTGRES_DB=plan_a API_V1_STR=/api/v1 SECRET_KEY=your-secret-key OPENAI_API_KEY=your-openai-key
Start the services with Docker Compose: docker compose up -d
Verify services are running: docker compose ps
Access the services:
- Frontend: http://localhost/
- Backend API: http://localhost:1314/api/v1/
- API docs: http://localhost:1314/docs

Notes:

If you modify environment variables, restart the services: docker compose restart
Logs can be viewed with: docker compose logs -f

Additional notes

Tips and caveats:

Ensure PostgreSQL is reachable and the credentials match the env vars; misconfigured DB settings will prevent startup.
The OPENAI_API_KEY should be kept secret; avoid committing it to version control.
For production deployments, consider mounting persistent volumes for DB data and logs, and configuring TLS/reverse proxy as needed.
The MCP integration expects standardized context; when wiring tools, ensure compatibility and proper authentication for external services.
If using custom API paths, adjust API_V1_STR accordingly and update frontend/backend configurations to point to the correct base URL.

Related MCP Servers

ReActMCP

141

ReActMCP is a reactive MCP client that empowers AI assistants to instantly respond with real-time, Markdown-formatted web search insights powered by the Exa API.

mcp-python-interpreter

MCP Python Interpreter: run python code. Python-mcp-server, mcp-python-server, Code Executor

supermcp

🚀 SuperMCP - Create multiple isolated MCP servers using a single connector. Build powerful Model Context Protocol integrations for databases (PostgreSQL, MSSQL) with FastAPI backend, React dashboard, and token-based auth. Perfect for multi-tenant apps and AI assistants.

mcp-lite-dev

共学《MCP极简开发》项目代码

mcp-yfinance

Real-time stock API with Python, MCP server example, yfinance stock analysis dashboard

MCPSecBench

MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols