MCPJungle Details

MCPJungle is a self-hosted MCP Gateway and Registry for AI agents. It serves as a central registry and gateway to manage Model Context Protocol (MCP) servers and the tools they expose. By consolidating MCP server registration, tool discovery, and access control, MCPJungle enables AI agents and clients to discover, group, and securely invoke tools from a single, unified gateway. The project provides a CLI, Docker-based deployment options, and enterprise-ready features such as tool grouping, access control, and observability to streamline MCP-based workflows across organizations.

Use Case

MCPJungle acts as a centralized registry and gateway for MCP servers and their tools. It supports both Streamable HTTP and STDIO transports, enabling you to register remote MCP servers and invoke their tools through a single endpoint. It also lets you create Tool Groups to expose a curated subset of tools to specific clients, manage enabling/disabling of tools and prompts, and integrate with clients like Claude or Cursor. Example use cases include registering a calculator MCP server (streamable_http) and a filesystem MCP server (stdio), listing and invoking tools, and creating Claude-specific tool groups.

Example usage from the docs:

  • Register a streamable HTTP MCP server:

  • mcpjungle register --name calculator --description "Provides some basic math tools" --url http://127.0.0.1:8000/mcp

  • Access tools via MCPJungle:

  • mcpjungle list tools

    <h1 class="text-2xl font-semibold mt-5 mb-3">Check tool usage</h1>
    mcpjungle usage calculator__multiply

    <h1 class="text-2xl font-semibold mt-5 mb-3">Call a tool</h1>
    mcpjungle invoke calculator__multiply --input '{"a": 100, "b": 50}'


  • Connect Claude to MCPJungle (example config):

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

  • Register a STDIO MCP server (filesystem):

  • {
    "name": "filesystem",
    "transport": "stdio",
    "description": "filesystem mcp server",
    "command": "npx",
    "args": ["-y", "@modelcontextprotocol/server-filesystem", "."]
    }

  • Example tool group usage:

  • $ mcpjungle create group -c ./claude-tools-group.json

    Tool Group claude-tools created successfully
    It is now accessible at the following streamable http endpoint:

    http://127.0.0.1:8080/v0/groups/claude-tools/mcp


    Available Tools (7)

    Examples & Tutorials

    Real example code and usage patterns directly from the documentation:

  • Quickstart: Start the server using Docker Compose and verify health

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

  • Start a local MCPJungle server via CLI installation (Homebrew)

  • brew install mcpjungle/mcpjungle/mcpjungle
    mcpjungle version

  • Register an MCP server (streamable HTTP)

  • mcpjungle register --name calculator --description "Provides some basic math tools" --url http://127.0.0.1:8000/mcp

  • Register a server via config file

  • cat ./calculator.json
    {
    "name": "calculator",
    "transport": "streamable_http",
    "description": "Provides some basic math tools",
    "url": "http://127.0.0.1:8000/mcp"
    }

    mcpjungle register -c ./calculator.json


  • List tools, check usage, and invoke

  • mcpjungle list tools

    <h1 class="text-2xl font-semibold mt-5 mb-3">Check tool usage</h1>
    mcpjungle usage calculator__multiply

    <h1 class="text-2xl font-semibold mt-5 mb-3">Call a tool</h1>
    mcpjungle invoke calculator__multiply --input '{"a": 100, "b": 50}'


  • Register a STDIO-based MCP server (filesystem)

  • {
    "name": "filesystem",
    "transport": "stdio",
    "description": "filesystem mcp server",
    "command": "npx",
    "args": ["-y", "@modelcontextprotocol/server-filesystem", "."]
    }

  • Deregister servers

  • mcpjungle deregister calculator
    mcpjungle deregister filesystem

  • Claude integration config

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

  • Cursor integration config

  • {
    "mcpServers": {
    "mcpjungle": {
    "url": "http://localhost:8080/mcp"
    }
    }
    }

  • Enabling/Disabling tools and prompts

  • <h1 class="text-2xl font-semibold mt-5 mb-3">disable a specific tool</h1>
    mcpjungle disable tool context7__get-library-docs
    <h1 class="text-2xl font-semibold mt-5 mb-3">re-enable the tool</h1>
    mcpjungle enable tool context7__get-library-docs

    <h1 class="text-2xl font-semibold mt-5 mb-3">disable all tools in a server</h1>
    mcpjungle disable tool context7

    <h1 class="text-2xl font-semibold mt-5 mb-3">disable the whole server</h1>
    mcpjungle disable server context7

    <h1 class="text-2xl font-semibold mt-5 mb-3">disable a prompt</h1>
    mcpjungle disable prompt "huggingface_Model Details"
    <h1 class="text-2xl font-semibold mt-5 mb-3">disable all prompts in a server</h1>
    mcpjungle disable prompt context7


  • Prompts examples

  • $ mcpjungle list prompts --server huggingface

    $ mcpjungle get prompt "huggingface__Model Details" --arg model_id="openai/gpt-oss-120b"


  • Tool Groups examples

  • {
    "name": "claude-tools",
    "description": "This group only contains tools for Claude Desktop to use",
    "included_tools": [\
    "filesystem__read_file",\
    "deepwiki__read_wiki_contents",\
    "time__get_current_time"\
    ]
    }

  • Example 2: Including entire servers with exclusions

  • {
    "name": "claude-tools",
    "description": "All tools from time and deepwiki servers except time__convert_time",
    "included_servers": ["time", "deepwiki"],
    "excluded_tools": ["time__convert_time"]
    }

  • Example 3: Mixing approaches

  • {
    "name": "comprehensive-tools",
    "description": "Mix of manual tools, server inclusion, and exclusions",
    "included_tools": ["filesystem__read_file"],
    "included_servers": ["time"],
    "excluded_tools": ["time__convert_time"]
    }

  • Tool Group access endpoint example

  • $ mcpjungle create group -c ./claude-tools-group.json

    Tool Group claude-tools created successfully
    It is now accessible at the following streamable http endpoint:

    http://127.0.0.1:8080/v0/groups/claude-tools/mcp


    Installation Guide

    Step-by-step installation instructions from the docs:

  • Install via Homebrew:

  • brew install mcpjungle/mcpjungle/mcpjungle

  • Verify installation:

  • mcpjungle version

  • Alternative: Docker image for production deployment:

  • docker pull mcpjungle/mcpjungle

  • Quick start with Docker Compose (local development):

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

    docker compose up -d


  • Health check:

  • curl http://localhost:8080/health

  • Register a remote STDIO or Streamable HTTP MCP server (examples in docs) as part of setup.

  • Integration Guides

    Frequently Asked Questions

    Is this your MCP?

    Claim ownership and get verified badge

    Repository Stats
    Important Notes

    Notes and warnings from the docs:

  • SSE support exists but is not yet mature.

  • Prompts are supported and registered when MCP servers provide them.

  • Enterprise mode enables stricter security policies, including authentication, ACLs, and observability; development mode disables telemetry by default.

  • OpenTelemetry metrics are available at /metrics when enabled; in enterprise mode, OTEL is enabled by default, while in development mode you must enable it via OTEL_ENABLED.

  • Tool Groups can expose only a subset of tools; prompts are not currently supported in Tool Groups; you cannot update an existing group—delete and recreate instead.
  • Prerequisites

    MCPJungle is distributed as a stand-alone binary. Install it via Homebrew or download from the Releases page. Docker-based deployments are supported via docker-compose. For persistence, a Postgres DSN can be supplied; otherwise a SQLite database file mcpjungle.db is created by default. No Node.js prerequisite is required for MCPJungle itself.

    Details
    Last Updated1/1/2026
    Websitegithub.com
    SourceGitHub

    Compare Alternatives

    Similar MCP Tools

    6 related tools
    Anki MCP Server

    Anki MCP Server

    A Model Context Protocol (MCP) server that enables AI assistants to interact with Anki, the spaced repetition flashcard application. The Anki MCP Server allows AI models to access Anki's card data, enabling features like automated flashcard creation, review, and management.

    1MCP Agent

    1MCP Agent

    A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one. The 1mcp-app/agent is an open-source project that provides a single entry point for multiple MCP servers, making it easier to manage and interact with various AI models and tools.

    Roundtable AI MCP Server

    Roundtable AI MCP Server

    Roundtable AI MCP Server is a zero-configuration local MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and a standardized interface. It coordinates specialized sub-agents from within your IDE to solve engineering problems in parallel, sharing context and synthesizing responses into a single, high-quality output. This documentation details installation, available MCP tools, integration with popular IDEs, and a broad ecosystem of specialized tools and CLIs that can be invoked as part of a roundtable-powered workflow, enabling developers to delegate tasks to the right AI for each facet of a problem without leaving their development environment.

    mcpmcp-server

    mcpmcp-server

    mcpmcp-server is a focused solution for discovering, setting up, and integrating MCP servers with your favorite clients to unlock AI-powered workflows. It streamlines how you connect MCP-powered servers to popular clients, enabling seamless AI-assisted interactions across your daily tools. The project emphasizes an approachable, config-driven approach to linking MCP servers with clients like Claude Desktop, while directing you to the homepage for variations across apps and platforms. This README highlights a practical JSON configuration example and notes on supported environments, helping you get started quickly and confidently.

    Imagen3-MCP

    Imagen3-MCP

    Imagen3-MCP is an image generation service based on Google's Imagen 3.0 that exposes its functionality through MCP (Model Control Protocol). The project provides a server to run a local MCP service that accesses Google Gemini-powered image generation, enabling developers to integrate advanced image synthesis into their applications. The documentation covers prerequisites (Gemini API key), installation steps for Cherry Studio, and a Cursor-based JSON configuration example for embedding the MCP server in broader tooling. This MCP is designed to be deployment-friendly, with configurable environment variables and optional proxy settings to adapt to various network environments.

    Anyquery MCP

    Anyquery MCP

    Anyquery MCP is the Model Context Protocol endpoint for the Anyquery SQL engine, enabling large language models (LLMs) like ChatGPT and Claude to connect to and query data through MCP. This MCP server acts as a bridge between LLMs and Anyquery’s data integrations, allowing LLMs to contextually access files, databases, and apps via the MCP interface. It complements Anyquery’s SQL querying capabilities by providing a standardized, secure channel for LLMs to request data access, execute SQL-like interactions, and receive structured results. The MCP integration is designed to be used in conjunction with Anyquery’s SQL runtime, including its MySQL-compatible server mode for client tooling, and is part of the broader MCP-enabled ecosystem described in the project docs.