mcp-manus
Production-ready MCP server with Manus.im integration
claude mcp add --transport stdio gianlucamazza-mcp-manus-server node path/to/mcp_manus/dist/index.js \ --env LOG_LEVEL="info" \ --env JWT_SECRET="your_jwt_secret" \ --env MANUS_API_KEY="your_api_key" \ --env OAUTH_CLIENT_ID="your_client_id" \ --env OAUTH_REDIRECT_URI="your_redirect_uri" \ --env OAUTH_CLIENT_SECRET="your_client_secret"
How to use
This MCP Manus Server provides a production-ready MCP endpoint integrated with Manus.im. It exposes a set of tools that can be invoked by MCP clients to query system information, echo messages, or check Manus credits, enabling workflow automation around Manus integration. The server uses OAuth 2.1 with PKCE for secure client authentication and supports resource indicators for fine-grained access control. To use it, configure an MCP client to point at the Manus server entry point (the Node.js runtime path shown in the mcp_config) and supply the required OAuth credentials and Manus API key. Once started, clients can request tools such as get_system_info, echo, and check_manus_credits, and can access resources like system status or Manus integration status via the provided MCP URIs.
How to install
Prerequisites:
- Node.js 20+ installed on the host
- Docker & Docker Compose installed (for containerized deployment)
- Git installed
Installation steps:
- Clone the repository: git clone https://github.com/your-org/mcp_manus.git
- Navigate to the project directory: cd mcp_manus
- Install dependencies: npm install
- Configure environment for development:
cp .env.example .env
Edit .env with your configuration (OAuth credentials, Manus API key, JWT secret, etc.)
- Run the development server: npm run dev
Docker deployment (optional):
- Build and run with Docker Compose: docker-compose -f docker/docker-compose.yml up -d
- If you use an HTTP proxy, start with the http profile: docker-compose -f docker/docker-compose.yml --profile http up -d
- Health check: curl http://localhost:8080/health
Additional notes
Tips and notes:
- Ensure environment variables are securely managed; avoid committing secrets. Prefer a secret manager in production.
- The server implements OAuth 2.1 with PKCE; ensure your OAuth provider is configured to issue access tokens with the expected scopes.
- For production, enable health checks and proper container security practices as described in the Security documentation.
- The available tools (get_system_info, echo, check_manus_credits) can be extended; follow the repository guidelines for adding new tools and updating tests.
- If you encounter issues with Manus API integration, verify the Manus API key and network access from the host or container.
- Logs are structured in JSON; set LOG_LEVEL to an appropriate level (debug/info/warn/error) for observability.
Related MCP Servers
ironcurtain
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
1xn-vmcp
vMCP - Virtual Model Context Protocol
prometheus
A Model Context Protocol (MCP) server implementation that provides AI agents with programmatic access to Prometheus metrics via a unified interface.
mcp-auth s
🔒 Reference MCP servers that demo how authentication works with the current Model Context Protocol spec.
openapi-to
Turns any OpenAPI/Swagger API into an MCP server. One MCP tool per endpoint, Streamable HTTP - for AI clients calling your REST API.
PlexMCP-OSS
The MCP gateway platform. PlexMCP gives you a unified gateway to manage, orchestrate, and secure your MCP servers.