fluidmcp
by Fluid-AI
Overview
Orchestrate multiple Model Context Protocol (MCP) servers from various sources (local config, GitHub, S3, registry) with a unified FastAPI gateway.
Installation
fluidmcp run examples/sample-config.json --file --start-serverEnvironment Variables
- FMCP_BEARER_TOKEN
- FMCP_SECURE_MODE
- MCP_CLIENT_SERVER_PORT
- MCP_CLIENT_SERVER_ALL_PORT
- MCP_FETCH_URL
- MCP_TOKEN
- MCP_INSTALLATION_DIR
- S3_BUCKET_NAME
- S3_ACCESS_KEY
- S3_SECRET_KEY
- S3_REGION
- FMCP_GITHUB_TOKEN
- GITHUB_TOKEN
Security Notes
CRITICAL: The system executes arbitrary commands and arguments specified in configuration files (loaded from registry, local files, S3 URLs, or GitHub repositories). If a user processes a configuration from an untrusted source, or if a trusted source is compromised, this can lead to Remote Code Execution (RCE) on the host machine. While API access can be secured with bearer tokens, this does not prevent malicious server definitions from being executed. Users must exercise extreme caution and only use configurations from fully trusted sources.
Similar Servers
fastapi_mcp
Automatically converts FastAPI endpoints into Model Context Protocol (MCP) tools for seamless integration with LLM agents.
mcphub
A hub for managing, orchestrating, and providing a unified API for various Model Context Protocol (MCP) servers and their tools, including user management, OAuth services, and discovery of external servers.
mcpstore
MCPStore acts as an orchestration layer for managing Microservice Context Protocol (MCP) services and adapting them as tools for AI frameworks like LangChain, AutoGen, and others.
mcp-compose
A secure MCP (Model Context Protocol) server that orchestrates calculator and string manipulation tools, offering OAuth2 authentication with GitHub. It implements advanced OAuth features like PKCE, resource indicators, and dynamic client registration, making it suitable for protected AI agent integrations and enterprise API management.