MCPJungle and mcp-gateway

Project A appears to be a more fully-featured, self-hosted gateway offering with a significantly larger community, while project B likely represents a simpler or earlier iteration of an MCP Gateway and Registry, making them competitors with A being the more mature and adopted solution.

MCPJungle
59
Established
mcp-gateway
40
Emerging
Maintenance 13/25
Adoption 10/25
Maturity 15/25
Community 21/25
Maintenance 0/25
Adoption 9/25
Maturity 15/25
Community 16/25
Stars: 898
Forks: 117
Downloads:
Commits (30d): 5
Language: Go
License: MPL-2.0
Stars: 80
Forks: 13
Downloads:
Commits (30d): 0
Language: Python
License: MIT-0
No Package No Dependents
Archived No Package No Dependents

About MCPJungle

mcpjungle/MCPJungle

Self-hosted MCP Gateway for AI agents

This tool helps developers and organizations centralize access to various AI agent tools. You register your existing Model Context Protocol (MCP) servers and their tools with MCPJungle, and then your AI agents (like Claude or Cursor) can access all of them through a single connection. It's designed for managing AI agent interactions in a private, secure environment.

AI Agent Management Internal Tooling Private AI Infrastructure Tool-calling Orchestration Enterprise AI

About mcp-gateway

aarora79/mcp-gateway

MCP Gateway and Registry

Provides centralized access to multiple Model Context Protocol (MCP) servers through an Nginx reverse proxy, enabling AI agents to discover and invoke tools dynamically across distributed backends. The Registry component offers both UI and programmatic interfaces for service discovery, health monitoring, and dynamic tool exploration via natural language queries. Supports multiple transport mechanisms (SSE and Streamable HTTP) with deployments spanning EC2 instances, EKS clusters, and AWS Lambda functions.

Scores updated daily from GitHub, PyPI, and npm data. How scores work