mcp-http-agent-md
Verified Safeby benhaotang
Overview
This server provides a Minimal Model Context Protocol (MCP) HTTP server for managing AI agent projects, structured tasks, and versioned history, enabling subagent orchestration and document management.
Installation
docker run --restart always -p 3000:3000 -e MAIN_API_KEY=your-main-api-key -e HOST=0.0.0.0 -v "$HOME/.config/mcp-http-agent-md/data":/app/data --name mcp-http-agent-md ghcr.io/benhaotang/mcp-http-agent-md:latestEnvironment Variables
- MAIN_API_KEY
- USE_EXTERNAL_AI
- AI_API_TYPE
- AI_API_KEY
- AI_MODEL
- AI_BASE_ENDPOINT
- AI_TIMEOUT
- AI_ATTACHMENT_TEXT_LIMIT
- LOCAL_OCR_MODEL_ENDPOINT
- LOCAL_OCR_MODEL
- LOCAL_OCR_API_KEY
- MISTRAL_AI_API
- MISTRAL_API_KEY
- HOST
- PORT
- BASE_PATH
- DATABASE_PATH
- MCP_SKIP_SERVERS
Security Notes
The project demonstrates robust security practices, including proper authentication and authorization (admin API key, user API keys, project-specific permissions), secure file handling (random file IDs, path sanitization, size limits, content-based type detection), and SQL injection prevention via prepared statements. The use of `execFile` for PDF processing is handled carefully with temporary directories and input sanitization. The broad CORS (`*`) is the only minor theoretical risk if deployed publicly without additional reverse proxy controls, but it is acceptable for a local or internal agent server.
Similar Servers
mcp-server
Provides a Model Context Protocol (MCP) server for AI agents to search and retrieve curated documentation for the Strands Agents framework, facilitating AI coding assistance.
tmcp
Build Model Context Protocol (MCP) servers for AI agents, providing schema-agnostic tools, resources, and prompts, with optional OAuth 2.1 authentication and distributed session management.
backlog-mcp-server
Integrate Backlog API with AI agents (e.g., Claude) to manage projects, issues, wikis, and Git repositories through natural language commands.
mcp-github-project-manager
AI-powered GitHub Project Management, including automated roadmap generation, sprint planning, issue triaging, task breakdown, and comprehensive project workflow automation.