Multi-model AI orchestration MCP server with code review, compare, and debate tools.
Multi-model AI orchestration MCP server with code review, compare, and debate tools.
This MCP server coordinates multiple models for the same task, enabling code review, comparison, and debate-style interactions across models. It exposes an orchestration layer to run prompts through several AI backends and surface aggregated results.
๐ ๏ธ Key Features
Multi-model orchestration for Claude, Claude-like skills, OpenAI, Gemini, and other agents
Code review, analysis, comparison, and debate tooling
MCP (Multi-Model Code Protocol) support for structured agent coordination
CLI-friendly and agent-friendly interfaces
Open-source MIT-licensed with Python 3.11+ compatibility
๐ Use Cases
Parallel model evaluation of programming tasks
Code analysis and cross-model reviews
Debated decisions across different AI agents
Multi-model decision logging for governance and QA
โก Developer Benefits
Clear integration points for multi-model workflows
Extensible with additional AI backends and agent capabilities
Visible project status via CI badges and PyPI distribution
โ ๏ธ Limitations
Based on available readme excerpt; specifics may vary by deployment
Model availability and compatibility depend on connected backends and tokens
Multi-MCP: Multi-Model Code Review and Analysis MCP Server for Claude Code
A multi-model AI orchestration MCP server for automated code review and LLM-powered analysis. Multi-MCP integrates with Claude Code CLI and OpenCode to orchestrate multiple AI models (OpenAI GPT, Anthropic Claude, Google Gemini) for code quality checks, security analysis (OWASP Top 10), and multi-agent consensus. Built on the Model Context Protocol (MCP), this tool enables Python developers and DevOps teams to automate code reviews with AI-powered insights directly in their development workflow.
Demo Video
Features
๐ Code Review - Systematic workflow with OWASP Top 10 security checks and performance analysis
๐ฌ Chat - Interactive development assistance with repository context awareness
๐ Compare - Parallel multi-model analysis for architectural decisions
๐พ Conversation Threading - Maintains context across multi-step reviews
๐ Low Latency - Response time = slowest model, not sum of all models
Quick Start
Prerequisites:
Python 3.11+
API key for at least one provider (OpenAI, Anthropic, Google, or OpenRouter)
Installation
Option 1: From Source
bash
# Clone and install
git clone https://github.com/religa/multi_mcp.git
cd multi_mcp
# Execute ./scripts/install.sh
make install
# The installer will:# 1. Install dependencies (uv sync)# 2. Generate your .env file# 3. Automatically add to Claude Code / OpenCode config (requires jq)# 4. Test the installation
Option 2: Manual Configuration
If you prefer not to run make install:
bash
# Install dependencies
uv sync# Copy and configure .envcp .env.example .env# Edit .env with your API keys
Add to Claude Code (~/.claude.json) or OpenCode (~/.opencode/opencode.json), replacing /path/to/multi_mcp with your actual clone path:
version:"1.0"models:# Add a new API modelmy-custom-gpt:litellm_model:openai/gpt-4oaliases:-customnotes:"My custom GPT-4o configuration"# Add a custom CLI modelmy-local-llm:provider:clicli_command:ollamacli_args:-"run"-"llama3.2"cli_parser:textaliases:-localnotes:"Local LLaMA via Ollama"# Override an existing model's settingsgpt-5-mini:constraints:temperature:0.5# Override default temperature
Merge behavior:
New models are added alongside package defaults
Existing models are merged (your settings override package defaults)
Aliases can be "stolen" from package models to your custom models
Usage Examples
Once installed in your MCP client (Claude Code or OpenCode), you can use these commands:
๐ฌ Chat - Interactive development assistance:
code
Can you ask Multi chat what's the answer to life, universe and everything?
๐ Code Review - Analyze code with specific models:
code
Can you multi codereview this module for code quality and maintainability using gemini-3 and codex?
๐ Compare - Get multiple perspectives (uses default models):
code
Can you multi compare the best state management approach for this React app?
๐ญ Debate - Deep analysis with critique:
code
Can you multi debate the best project code name for this project?
Enabling Allowlist
Edit ~/.claude/settings.json and add the following lines to permissions.allow to enable Claude Code to use Multi MCP without blocking for user permission:
Run multi:models to see all available models and aliases.
CLI Models
Multi-MCP can execute CLI-based AI models (like Gemini CLI, Codex CLI, or Claude CLI) alongside API models. CLI models run as subprocesses and work seamlessly with all existing tools.
Benefits:
Use models with full tool access (file operations, shell commands)
Mix API and CLI models in compare and debate workflows
Leverage local CLIs without API overhead
Built-in CLI Models:
gemini-cli (alias: gem-cli) - Gemini CLI with auto-edit mode
codex-cli (alias: cx-cli) - Codex CLI with full-auto mode
claude-cli (alias: cl-cli) - Claude CLI with acceptEdits mode
version:"1.0"models:my-ollama:provider:clicli_command:ollamacli_args:-"run"-"codellama"cli_parser:text# "json", "jsonl", or "text"aliases:-ollamanotes:"Local CodeLlama via Ollama"
Prerequisites:
CLI models require the respective CLI tools to be installed:
Multi-MCP includes a standalone CLI for code review without needing an MCP client.
โ ๏ธ Note: The CLI is experimental and under active development.
bash
# Review a directory
multi src/
# Review specific files
multi src/server.py src/config.py
# Use a different model
multi --model mini src/
# JSON output for CI/pipelines
multi --json src/ > results.json
# Verbose logging
multi -v src/
# Specify project root (for CLAUDE.md loading)
multi --base-path /path/to/project src/
Verify API keys are valid and have sufficient credits
Debug mode:
bash
export LOG_LEVEL=DEBUG # INFO is default
uv run python -m multi_mcp.server
Check logs in logs/server.log for detailed information.
FAQ
Q: Do I need all three AI providers?
A: No, just one API key (OpenAI, Anthropic, or Google) is enough to get started.
Q: Does it truly run in parallel?
A: Yes! When you use codereview, compare or debate tools, all models are executed concurrently using Python's asyncio.gather(). This means you get responses from multiple models in the time it takes for the slowest model to respond, not the sum of all response times.
Q: How many models can I run at the same time?
A: There's no hard limit! You can run as many models as you want in parallel. In practice, 2-5 models work well for most use cases. All tools use your configured default models (typically 2-3), but you can specify any number of models you want.