Skip to content
Back to search

MCPJungle

One place to manage & connect to all your MCP servers

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/mcpjungle--mcpjungle/badge.svg)](/listings/mcpjungle--mcpjungle)

HTML

<a href="/listings/mcpjungle--mcpjungle"><img src="/api/listings/mcpjungle--mcpjungle/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

This quickstart guide will show you how to: 1. Start the mcpjungle server locally using `docker compose` 2. Add an MCP server in mcpjungle 3. Connect your Claude Desktop to mcpjungle to access your MCP tools

Start the server

Fetch the `docker-compose.yaml` and start the mcpjungle server:

curl -O https://raw.githubusercontent.com/mcpjungle/MCPJungle/refs/heads/main/docker-compose.yaml
docker compose up -d

This exposes mcpjungle's streamable http mcp server at `http://localhost:8080/mcp` by default.

Add an MCP server

1. Download the `mcpjungle` CLI on your local machine either using brew or directly from the [Releases Page](https://github.com/mcpjungle/MCPJungle/releases).

brew install mcpjungle/mcpjungle/mcpjungle

2. Add the [context7](https://context7.com/) MCP server to mcpjungle using the CLI:

mcpjungle register --name context7 --url https://mcp.context7.com/mcp

You should see output similar to this:

Connect to mcpjungle

In your Claude Desktop, add the configuration for mcpjungle MCP server:

{
  "mcpServers": {
    "mcpjungle": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:8080/mcp",
        "--allow-http"
      ]
    }
  }
}

Once you have added the configuration, try asking claude something simple:

Use context7 to get the documentation for `/lodash/lodash`

Claude will then attempt to call the `context7__get-library-docs` tool via MCPJungle, which will return the documentation for the Lodash library.

<p align="center"> </p>

You now have a working MCP setup with a single unified endpoint!

Next, explore the complete documentation at [docs.mcpjungle.com](https://docs.mcpjungle.com/) and the [public roadmap](https://docs.mcpjungle.com/roadmap).

---

<details> <summary>Legacy README reference</summary>

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 122 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <h1 align="center">
  2. MCPJungle
  3. </h1>
  4. <p align="center">
  5. <strong>Run all your MCP servers behind one endpoint</strong>
  6. </p>
  7. <p align="center">
  8. <a href="https://docs.mcpjungle.com" style="text-decoration: none;">
  9. <img src="https://img.shields.io/badge/Documentation-docs.mcpjungle.com-blue?style=flat-square&logo=book" alt="Documentation" style="max-width: 100%;">
  10. </a>
  11. <a href="https://github.com/mcpjungle/mcpjungle/pkgs/container/mcpjungle" style="text-decoration: none;">
  12. <img src="https://img.shields.io/badge/GHCR-available-green.svg?style=flat-square&logo=github" alt="GHCR" style="max-width: 100%;">
  13. </a>
  14. <a href="https://discord.gg/CapV4Z3krk" style="text-decoration: none;">
  15. <img src="https://img.shields.io/badge/Discord-MCPJungle-5865F2?style=flat-square&logo=discord&logoColor=white" alt="Discord" style="max-width: 100%;">
  16. </a>
  17. </p>
  18. MCPJungle is a self-hosted MCP gateway for developers and teams who want to manage multiple MCP servers without scattered client configurations, duplicated setup, or inconsistent access control.
  19. Use it **locally** to keep your personal MCP setup clean, or run it as **shared infrastructure** for a team with centralized discovery, access control, and observability.
  20. ![diagram](./assets/mcpjungle-diagram/april-2026/mcpjungle-diagram.png)
  21. Instead of wiring every MCP server into every AI client, register your servers once in MCPJungle and let Claude, Cursor, Codex, or your own Agents connect to a single MCP endpoint.
  22. ## Why MCPJungle?
  23. MCP is powerful, but managing many MCP servers gets messy fast.
  24. Without a gateway:
  25. - 🔌 Every client needs its own MCP server configuration
  26. - 🧩 Tools, prompts, and resources are scattered across different servers
  27. - 🔐 Access control is duplicated or missing
  28. - 👥 Teams have no shared view of available MCP tools
  29. - 🛠️ Local setups become hard to reproduce
  30. MCPJungle gives you a single control point:
  31. - 🌐 One MCP endpoint for Claude, Cursor, Copilot, and custom agents
  32. - 🗂️ One place to register and manage MCP servers
  33. - 🔎 Unified discovery for tools, prompts, and resources
  34. - 🎛️ Optional tool groups to expose only the tools a client should see
  35. - 📊 Simple access-control and observability hooks for shared deployments
  36. Start with a local setup. Scale to a shared team gateway when you need it.
  37. ![MCPJungle dashboard UI](./docs/images/dashboard-ui.png)
  38. ## Documentation
  39. Mcpjungle documentation has a new home: [https://docs.mcpjungle.com](https://docs.mcpjungle.com).
  40. Please prefer the docs site over this README for the latest guides, reference, and operational details.
  41. Your AI Clients can also access the docs using its MCP server `https://docs.mcpjungle.com/mcp`!
  42. ## Quickstart
  43. This quickstart guide will show you how to:
  44. 1. Start the mcpjungle server locally using `docker compose`
  45. 2. Add an MCP server in mcpjungle
  46. 3. Connect your Claude Desktop to mcpjungle to access your MCP tools
  47. ### Start the server
  48. Fetch the `docker-compose.yaml` and start the mcpjungle server:
  49. ```bash
  50. curl -O https://raw.githubusercontent.com/mcpjungle/MCPJungle/refs/heads/main/docker-compose.yaml
  51. docker compose up -d
  52. ```
  53. This exposes mcpjungle's streamable http mcp server at `http://localhost:8080/mcp` by default.
  54. ### Add an MCP server
  55. 1. Download the `mcpjungle` CLI on your local machine either using brew or directly from the [Releases Page](https://github.com/mcpjungle/MCPJungle/releases).
  56. ```bash
  57. brew install mcpjungle/mcpjungle/mcpjungle
  58. ```
  59. 2. Add the [context7](https://context7.com/) MCP server to mcpjungle using the CLI:
  60. ```bash
  61. mcpjungle register --name context7 --url https://mcp.context7.com/mcp
  62. ```
  63. You should see output similar to this:
  64. ![register-context7](./docs/images/register-context7.png)
  65. ### Connect to mcpjungle
  66. In your Claude Desktop, add the configuration for mcpjungle MCP server:
  67. ```json
  68. {
  69. "mcpServers": {
  70. "mcpjungle": {
  71. "command": "npx",
  72. "args": [
  73. "mcp-remote",
  74. "http://localhost:8080/mcp",
  75. "--allow-http"
  76. ]
  77. }
  78. }
  79. }
  80. ```
  81. Once you have added the configuration, try asking claude something simple:
  82. ```text
  83. Use context7 to get the documentation for `/lodash/lodash`
  84. ```
  85. Claude will then attempt to call the `context7__get-library-docs` tool via MCPJungle, which will return the documentation for the Lodash library.
  86. <p align="center">
  87. <img src="./assets/quickstart-claude-call-tool.png" alt="claude calls context7 tool via mcpjungle" height="400">
  88. </p>
  89. You now have a working MCP setup with a single unified endpoint!
  90. Next, explore the complete documentation at [docs.mcpjungle.com](https://docs.mcpjungle.com/) and the [public roadmap](https://docs.mcpjungle.com/roadmap).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.