Which integrations are available for this server?

Enables multi-agent workflows using CrewAI framework for code review, refactoring, debugging, documentation, architecture analysis, and feature development tasks Supports multi-agent orchestration capabilities through LangChain framework for intelligent code analysis and development workflows

How do I use MeshAI MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MeshAI MCP Server review this Python function for security issues and suggest improvements" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

MeshAI MCP Server

by meshailabs-org

Overview Schema Related Servers Discussions Admin

Python

Remote

MeshAI MCP Server

Build Status Docker Image PyPI version Python 3.8+

A standalone Model Context Protocol (MCP) server that enables Claude Code and other MCP-compatible tools to leverage MeshAI's multi-agent orchestration capabilities.

🚀 Features

🤖 Multi-Agent Workflows: 6 pre-configured workflows for code review, refactoring, debugging, documentation, and more
🧠 Intelligent Agent Selection: Automatically selects appropriate AI agents based on task content
🔧 Framework Agnostic: Works with agents built on LangChain, CrewAI, AutoGen, and other frameworks
🐋 Docker Ready: Full Docker support with development and production configurations
📦 Easy Installation: Available as PyPI package or Docker container
🔄 Fallback Protocol: Works without official MCP package using built-in implementation

Related MCP server: Consult LLM MCP

📋 Quick Start

Option 1: Docker with stdio (Claude Code)

# Run with Docker for Claude Code integration
docker run -it \
  -e MESHAI_API_URL=http://localhost:8080 \
  -e MESHAI_API_KEY=your-api-key \
  ghcr.io/meshailabs/meshai-mcp-server:latest

# Or with docker-compose
git clone https://github.com/meshailabs/meshai-mcp.git
cd meshai-mcp
cp .env.template .env  # Edit with your settings
docker-compose up

Option 2: HTTP Server Mode

# Run as HTTP API server
docker run -p 8080:8080 \
  -e MESHAI_API_URL=http://localhost:8080 \
  ghcr.io/meshailabs/meshai-mcp-server:latest \
  meshai-mcp-server serve --transport http

# Test the HTTP API
curl -H "Authorization: Bearer dev_your-api-key" \
     http://localhost:8080/v1/tools

Option 3: PyPI Installation

# Install from PyPI
pip install meshai-mcp-server

# Run in stdio mode (for Claude Code)
export MESHAI_API_URL=http://localhost:8080
export MESHAI_API_KEY=your-api-key
meshai-mcp-server

# Or run as HTTP server
meshai-mcp-server serve --transport http --port 8080

Option 4: Development Setup

# Clone and install
git clone https://github.com/meshailabs/meshai-mcp.git
cd meshai-mcp
pip install -e ".[dev]"

# Run in development mode
python -m meshai_mcp.cli serve --dev --transport http

🔧 Configuration

Environment Variables

Variable	Description	Default	Required
`MESHAI_API_URL`	MeshAI API endpoint	`http://localhost:8080`	Yes
`MESHAI_API_KEY`	API key for authentication	None	For stdio mode
`MESHAI_LOG_LEVEL`	Logging level	`INFO`	No

🔐 Authentication

For HTTP Mode:

API Key Required: Pass via Authorization: Bearer YOUR_API_KEY header
Development Keys: Use dev_ prefix for testing (e.g., dev_test123)
Rate Limiting: 100 requests/hour for development, configurable for production

For stdio Mode:

Environment Variable: Set MESHAI_API_KEY for backend communication
No HTTP Auth: Authentication handled by Claude Code

Claude Code Integration

stdio Transport (Recommended):

{
  "servers": {
    "meshai": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "-e", "MESHAI_API_URL=${MESHAI_API_URL}",
        "-e", "MESHAI_API_KEY=${MESHAI_API_KEY}",
        "ghcr.io/meshailabs/meshai-mcp-server:latest"
      ],
      "transport": "stdio"
    }
  }
}

HTTP Transport (For hosted deployments):

{
  "servers": {
    "meshai": {
      "command": "curl",
      "args": [
        "-X", "POST",
        "-H", "Authorization: Bearer ${MESHAI_MCP_API_KEY}",
        "-H", "Content-Type: application/json",
        "-d", "@-",
        "https://your-mcp-server.com/v1/mcp"
      ],
      "transport": "http"
    }
  }
}

Local pip Installation:

{
  "servers": {
    "meshai": {
      "command": "meshai-mcp-server",
      "transport": "stdio",
      "env": {
        "MESHAI_API_URL": "${MESHAI_API_URL}",
        "MESHAI_API_KEY": "${MESHAI_API_KEY}"
      }
    }
  }
}

🛠️ Available Workflows

1. Code Review (`mesh_code_review`)

Comprehensive code review with security and best practices analysis.

Agents: code-reviewer, security-analyzer, best-practices-advisor

2. Refactor & Optimize (`mesh_refactor_optimize`)

Refactor code with performance optimization and test generation.

Agents: code-optimizer, performance-analyzer, test-generator

3. Debug & Fix (`mesh_debug_fix`)

Debug issues and generate tests for fixes.

Agents: debugger-expert, log-analyzer, test-generator

4. Document & Explain (`mesh_document_explain`)

Generate documentation and explanations with examples.

Agents: doc-writer, code-explainer, example-generator

5. Architecture Review (`mesh_architecture_review`)

Comprehensive architecture analysis and recommendations.

Agents: system-architect, performance-analyst, security-auditor

6. Feature Development (`mesh_feature_development`)

End-to-end feature development from design to testing.

Agents: product-designer, senior-developer, test-engineer, doc-writer

🌐 HTTP API Usage

Starting HTTP Server

# Using Docker
docker run -p 8080:8080 \
  -e MESHAI_API_URL=http://localhost:8080 \
  ghcr.io/meshailabs/meshai-mcp-server:latest \
  meshai-mcp-server serve --transport http

# Using pip
meshai-mcp-server serve --transport http --port 8080

API Endpoints

Endpoint	Method	Description	Auth Required
`/health`	GET	Health check	No
`/v1/tools`	GET	List available tools	Yes
`/v1/workflows`	GET	List workflows	Yes
`/v1/resources`	GET	List resources	Yes
`/v1/mcp`	POST	Execute MCP request	Yes
`/v1/stats`	GET	Usage statistics	Yes
`/docs`	GET	API documentation	No

Usage Examples

# Health check (no auth required)
curl http://localhost:8080/health

# List available tools
curl -H "Authorization: Bearer dev_test123" \
     http://localhost:8080/v1/tools

# Execute a workflow
curl -X POST \
     -H "Authorization: Bearer dev_test123" \
     -H "Content-Type: application/json" \
     -d '{"method":"mesh_code_review","id":"test","params":{"files":"app.py"}}' \
     http://localhost:8080/v1/mcp

# Get usage stats
curl -H "Authorization: Bearer dev_test123" \
     http://localhost:8080/v1/stats

🐋 Docker Deployment

Development Setup

# Development with hot reload
docker-compose -f docker-compose.dev.yml up

# Run tests
docker-compose -f docker-compose.dev.yml run --rm mcp-tests

# With mock API
docker-compose -f docker-compose.dev.yml --profile mock up

Production Considerations

For production deployment:

Use proper API key management
Set up rate limiting and monitoring
Configure HTTPS/TLS termination
Implement proper logging and metrics
Consider using a reverse proxy (nginx, Traefik)
Set resource limits and scaling policies

🧪 Development

Setup Development Environment

# Clone repository
git clone https://github.com/meshailabs/meshai-mcp.git
cd meshai-mcp

# Install in development mode
pip install -e ".[dev]"

# Install pre-commit hooks
pre-commit install

# Run tests
pytest tests/ -v

# Run with coverage
pytest tests/ -v --cov=src/meshai_mcp --cov-report=html

Code Quality

# Format code
black src tests
isort src tests

# Type checking
mypy src/meshai_mcp

# Linting
flake8 src tests

Building Docker Images

# Build production image
docker build -t meshai-mcp-server .

# Build development image
docker build -f Dockerfile.dev --target development -t meshai-mcp-server:dev .

# Multi-architecture build
docker buildx build --platform linux/amd64,linux/arm64 -t meshai-mcp-server:multi .

📚 Documentation

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

Development Workflow

Fork the repository
Create a feature branch
Make your changes
Add tests for new functionality
Run the test suite
Submit a pull request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🆘 Support

GitHub Issues: Report bugs or request features
Documentation: docs.meshai.dev
Discord: Join our community

🗺️ Roadmap

HTTP transport support for MCP
WebSocket transport for real-time communication
Custom workflow configuration via YAML
Plugin system for custom agents
Prometheus metrics integration
Official MCP package integration when available

Built with ❤️ by the MeshAI Labs team.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Writingmate MCPOAuth
ai.writingmate
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
AI & Machine Learning Image & Video Processing
1
toolweaveOAuth
io.github.andreysparish
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
App Automation AI & Machine Learning Agent Orchestration
2
QuallaaOAuth
com.quallaa
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
AI & Machine Learning Communication
2
RogerRat A
io.github.opcastil11
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
Communication Agent Orchestration
21

Related MCP Servers

OpenAI Agents MCP Server
Agent Orchestration Search RAG Systems
lroolle
F
license
B
quality
D
maintenance
A Model Context Protocol server that enables Claude users to access specialized OpenAI agents (web search, file search, computer actions) and a multi-agent orchestrator through the MCP protocol.
Updated 2 years ago (2025-03-14 16:23 UTC)
4
10
-
Consult LLM MCP
Code Execution Autonomous Agents
raine
A
license
A
quality
A
maintenance
An MCP server that lets Claude Code consult stronger AI models (o3, Gemini 2.5 Pro, DeepSeek Reasoner) when you need deeper analysis on complex problems.
Updated 17 hours ago (2026-09-22 17:16 UTC)
1
102 npm
138
MIT
Gemini MCP
Code Analysis Developer Tools
emmron
A
license
C
quality
F
maintenance
An AI-powered Model Context Protocol server for Claude Code that provides code intelligence tools including codebase analysis, task management, component generation, and deployment configuration.
Updated 10 months ago (2025-11-09 19:05 UTC)
23
16
GPL 3.0
BlenderMCP
Eminemminem
A
license
B
quality
D
maintenance
Connects Blender to Claude AI through the Model Context Protocol, enabling AI-assisted 3D modeling, scene creation, and manipulation through natural language commands.
Updated a year ago (2025-07-18 01:26 UTC)
17
2
MIT

MeshAI MCP Server

🚀 Features

📋 Quick Start

Option 1: Docker with stdio (Claude Code)

Option 2: HTTP Server Mode

Option 3: PyPI Installation

Option 4: Development Setup

🔧 Configuration

Environment Variables

🔐 Authentication

For HTTP Mode:

For stdio Mode:

Claude Code Integration

stdio Transport (Recommended):

HTTP Transport (For hosted deployments):

Local pip Installation:

🛠️ Available Workflows

1. Code Review (mesh_code_review)

2. Refactor & Optimize (mesh_refactor_optimize)

3. Debug & Fix (mesh_debug_fix)

4. Document & Explain (mesh_document_explain)

5. Architecture Review (mesh_architecture_review)

6. Feature Development (mesh_feature_development)

🌐 HTTP API Usage

Starting HTTP Server

API Endpoints

Usage Examples

🐋 Docker Deployment

Development Setup

Production Considerations

🧪 Development

Setup Development Environment

Code Quality

Building Docker Images

📚 Documentation

🤝 Contributing

Development Workflow

📝 License

🆘 Support

🗺️ Roadmap

Resources

Related MCP Connectors

Related MCP Servers

OpenAI Agents MCP Server

Consult LLM MCP

Gemini MCP

BlenderMCP

1. Code Review (`mesh_code_review`)

2. Refactor & Optimize (`mesh_refactor_optimize`)

3. Debug & Fix (`mesh_debug_fix`)

4. Document & Explain (`mesh_document_explain`)

5. Architecture Review (`mesh_architecture_review`)

6. Feature Development (`mesh_feature_development`)