# mcpjungle/MCPJungle

> Self-hosted MCP gateway that lets you register multiple MCP servers once and expose them through a single endpoint for Claude, Cursor, Codex and custom agents.

- Magnitude: 3.4 out of 10 — Breakout
- Stars: 1,575 total · Not enough measurements today
- Star trust: star growth looks organic
- Category: AI agents · Language: Go · License: MPL-2.0 · Created: 2025-05-15 · Last push: 2026-11-03
- GitHub: https://github.com/mcpjungle/MCPJungle · Homepage: https://docs.mcpjungle.com · Page: https://gitnova.dev/en/r/mcpjungle/MCPJungle

## Useful for

- Run a local MCP gateway via docker compose and connect Claude Desktop to one endpoint
- Register a remote MCP server like context7 with the CLI and use its tools from any client
- Deploy a shared team gateway with centralized discovery and access control for MCP tools

## Why it’s here

- There are not enough fresh counter measurements for today's UTC day. The gain is unknown.
- Over the last two days the pace is 2.3× that of the previous week and a half.
- Elevated gains were measured on the last 3 completed UTC days in a row. Continued growth is not guaranteed.
- GitHub Trending Go today: #13, +47 stars.
- About 7 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 199
- Issues and pull requests: 305
- Watchers: 8
- Average over the last week: 37 per day
- Usual pace: 1 per day
- Latest release: 0.4.7 (2026-10-30)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-06 … 2026-11-04: 2, 2, 2, 0, 0, 2, 0, 0, 1, 3, 2, 0, 3, 0, 3, 5, 0, 0, 0, 1, 0, 2, 0, 2, 1, 2, 110, 94, 40, None

## Spotted in now

- GitHub Trending Go today: #13, +47 stars

## Similar by description

1. **Niconomics-9/mcp-context-forge** — 0.0 · Quiet · Python · Not enough measurements today
   An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.
   Full card: https://gitnova.dev/en/r/Niconomics-9/mcp-context-forge.md
2. **QuantumNous/new-api** — 3.3 · Steady · Language models · Go · +51 stars measured 2026-11-04, 00:20–12:16 UTC, ≈ 93 by evening
   Self-hosted AI gateway that aggregates multiple LLM providers behind a unified OpenAI-, Claude-, or Gemini-compatible API with routing, access, and cost management.
   Full card: https://gitnova.dev/en/r/QuantumNous/new-api.md
3. **AgenticResourceRegistry/AgenticResourceRegistry** — 0.9 · Quiet · AI agents · Python · +0 stars measured 2026-11-04, 00:27–12:26 UTC, ≈ 0 by evening
   A self-hosted registry for sharing coding agent resources across a team: Skills, MCP clients, prompts and agent files in one place with usage analytics. Works with Claude Code, Cursor, Kiro, Codex and more.
   Full card: https://gitnova.dev/en/r/AgenticResourceRegistry/AgenticResourceRegistry.md
4. **esurovtsev/spring-mcp-remote-sse** — 0.0 · Quiet · Java · +0 stars measured 2026-11-04, 11:39–12:28 UTC, ≈ 0 by evening
   Remote MCP (Model Context Protocol) server built with Spring Boot and SSE. Demonstrates how to register tools, configure endpoints, and stream results to connected LLM clients using the Spring AI MCP SDK.
   Full card: https://gitnova.dev/en/r/esurovtsev/spring-mcp-remote-sse.md
5. **HarnessRouter/harnessrouter** — 4.2 · Breakout · AI agents · Python · +66 stars measured 2026-11-04, 00:20–12:13 UTC, ≈ 133 by evening
   Self-hosted gateway that turns existing agent harnesses (Codex, Claude Code, Aider, etc.) into pluggable backends behind one OpenAI-compatible API via the open Unified Harness Protocol.
   Full card: https://gitnova.dev/en/r/HarnessRouter/harnessrouter.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-04 12:30 UTC, updated every 30 minutes.