MCP 服务器

MCP Multiagent Bridge

Enables secure coordination between multiple LLM agents through authenticated messaging, status updates, and conversation management. Features automatic secret redaction, rate limiting, and audit trails for safe multi-agent collaboration in development environments.

README

MCP Multiagent Bridge

Production-ready Python MCP server for secure multi-agent coordination with comprehensive safeguards.

Overview

Enables multiple LLM agents (Claude, Codex, GPT, etc.) to collaborate safely through the Model Context Protocol without sharing workspaces or credentials. Built with security-first architecture and production-grade safeguards.

Use cases:

Backend agent coordinating with frontend agent on different codebases
Security review agent validating changes from development agent
Specialized agents collaborating on complex multi-step workflows
Any scenario requiring isolated agents to communicate securely

Key Features

🔒 Security Architecture

Authentication & Authorization:

HMAC-SHA256 session token authentication
Automatic secret redaction (API keys, passwords, tokens, private keys)
3-hour session expiration with automatic cleanup
SQLite WAL mode for atomic, race-condition-free operations

4-Stage YOLO Guard™: Command execution (optional) requires multiple confirmation layers:

Environment gate - explicit YOLO_MODE=1 opt-in
Interactive typed confirmation phrase
One-time validation code (prevents automation)
Time-limited approval tokens (5-minute TTL, single-use)

Rate Limiting:

Token bucket algorithm with configurable windows
Default: 10 requests/minute, 100/hour, 500/day
Per-session tracking with automatic reset
Prevents abuse while allowing legitimate bursts

Audit Trail:

Comprehensive JSONL logging of all operations
Timestamps, session IDs, actions, results
Tamper-evident sequential logging
Supports compliance and forensic analysis

🏗️ Production-Ready Architecture

Message-only bridge - No auto-execution, returns proposals only
Schema validation - Strict JSON schemas for all MCP tools
Command validation - Configurable whitelist/blacklist patterns
Comprehensive error handling - Graceful degradation, informative errors
Extensible design - Plugin architecture for future backends

📦 Platform Support

Works with any MCP-compatible LLM:

Claude Code, Claude Desktop, Claude API
OpenAI models (via MCP adapters)
Anthropic API models
Custom/future models (not tied to specific backend)

Installation

# Clone repository
git clone https://github.com/dannystocker/mcp-multiagent-bridge.git
cd mcp-multiagent-bridge

# Install dependencies
pip install mcp>=1.0.0

# Run tests
python test_security.py

Full setup: See QUICKSTART.md

Documentation

Getting Started:

QUICKSTART.md - 5-minute setup guide
EXAMPLE_WORKFLOW.md - Real-world collaboration scenarios

Security & Compliance:

SECURITY.md - Threat model, responsible disclosure policy
YOLO_MODE.md - Command execution safety guide
Policy compliance: Anthropic AUP, OpenAI Usage Policies

Contributing:

CONTRIBUTING.md - Development setup, PR workflow
LICENSE - MIT License

Technical Stack

Python 3.11+ - Modern Python with type hints
SQLite - Atomic operations with WAL mode
MCP Protocol - Model Context Protocol integration
pytest - Comprehensive test suite
CI/CD - GitHub Actions (tests, security scanning, linting)

Project Statistics

Lines of Code: ~5,200 (including tests + documentation)
Test Coverage: Core security components verified
Documentation: 2,000+ lines across 7 markdown files
Dependencies: 1 (mcp, pinned for reproducibility)
License: MIT

Development

# Install dev dependencies
pip install -r requirements.txt

# Install pre-commit hooks
pip install pre-commit
pre-commit install

# Run test suite
pytest

# Run security tests
python test_security.py

See CONTRIBUTING.md for complete development workflow.