FluidMCP CLI

Orchestrate multiple MCP servers with a single configuration file

⚡ Quick Start - Run Multiple MCP Servers

The main power of FluidMCP is running multiple MCP servers from a single configuration file over a unified FastAPI endpoint.

Create aconfig.jsonfile with your MCP servers:

{ "mcpServers": { "google-maps": { "command": "npx", "args": ["-y", "@google-maps/mcp-server"], "env": { "GOOGLE_MAPS_API_KEY": "your-api-key" } }, "filesystem": { "command": "npx", "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/allowed/files"], "env": {} } } }

fluidmcp run config.json --file --start-server

- Install and configure all MCP servers listed in your config
- Launch them through a unified FastAPI gateway
- Make them available athttp://localhost:8099
- Provide automatic API documentation athttp://localhost:8099/docs

- Define multiple MCP servers in a single JSON configuration file
- Launch all servers with one command:fluidmcp run --file <config.json>
- Unified FastAPI gateway serving all your MCP tools

- Install MCP packages withfluidmcp install author/package@version
- Automatic dependency resolution and environment setup
- Support for npm, Python, and custom MCP servers

- Unified HTTP endpoints for all MCP tools
- Server-Sent Events (SSE) streaming support
- Swagger documentation at/docs

- Bearer token authentication
- Secure mode with encrypted communications
- Environment variable encryption for API keys

fluidmcp run author/package@version --start-server

fluidmcp run config.json --file --secure --token your_token --start-server

fluidmcp run "https://bucket.s3.amazonaws.com/config.json" --s3

- --start-server– Starts FastAPI server
- --master– Use S3-driven config
- --file– Run from local config.json
- --s3– Run from S3 URL
- --secure– Enable secure token mode
- --token <token>– Custom bearer token
- --verbose– Enable verbose logging (DEBUG level)

fluidmcp install author/package@version --master fluidmcp run all --master

# S3 Credentials (used in --master mode) export S3_BUCKET_NAME="..." export S3_ACCESS_KEY="..." export S3_SECRET_KEY="..." export S3_REGION="..." # Registry access export MCP_FETCH_URL="https://registry.fluidmcp.com/fetch-mcp-package" export MCP_TOKEN="..."

fluidmcp edit-env <author/package@version>

Displays FluidMCP version, Python version, and installation path.

# Validate a local configuration file fluidmcp validate config.json --file # Validate an installed package fluidmcp validate author/package@version

- Configuration file structure and resolution
- Command availability in system PATH
- Required environment variables (marked withrequired: true)
- Optional environment variables and tokens
- Metadata.json existence for installed packages

Note:Environment variable lookup is case-insensitive. For example, if your config specifiesgithub_token, the validator will check bothgithub_tokenandGITHUB_TOKENin your environment.

The command distinguishes betweenerrors(fatal issues) andwarnings(non-fatal issues):

- Missing commands in PATH
- Missing required environment variables
- Configuration resolution failures

- Missing optional environment variables
- Missing TOKEN variables not explicitly marked as required

✔ Configuration is valid with no issues found.

⚠️ Configuration is valid with warnings: - Optional env var 'DEBUG_MODE' is not set (server: test-server) - Token env var 'GITHUB_TOKEN' is not set (server: github-server) ✔ No fatal errors found. You may proceed, but consider addressing the warnings above.

❌ Configuration validation failed with errors: - Command 'nonexistent-command' not found in PATH (server: test-server) - Missing required env var 'API_KEY' (server: test-server) ⚠️ Warnings: - Optional env var 'DEBUG_MODE' is not set (server: test-server)

.fmcp-packages/ └── Author/ └── Package/ └── Version/ ├── metadata.json └── [tool files]

{ "mcpServers": { "maps": { "command": "npx", "args": ["-y", "@package/server"], "env": { "API_KEY": "xxx" } } } }

fluidmcp install Google_Maps/google-maps@0.6.2 fluidmcp run all

import requests, json url = "http://localhost:8099/google-maps/mcp" payload = { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "maps_search_places", "arguments": { "query": "coffee shops in San Francisco" } } } response = requests.post(url, json=payload) print(json.dumps(response.json(), indent=2))

curl -N -X POST http://localhost:8099/package/sse \ -H "Content-Type: application/json" \ -d @payload.json

- sse/start
- sse/stream
- sse/message
- sse/tools_call

Useful for LLMs, web scraping, or AI workflows that stream data.

FluidMCP is open for collaboration. We welcome contributions from the community!

- Contributing Guide: SeeCONTRIBUTING.mdfor development setup and guidelines
- Report Issues: Open an issue onGitHub
- Submit PRs: Follow our contribution guidelines to submit pull requests

his repository contains a fully functional MCP (Model Context Protocol) server, providing solutions for Constraint Satisfaction Problems (CSP) and Linear Programming (LP). It is based on the gurddy package and supports solving a variety of classic problems.