:deciduous_tree: MCPJungle :deciduous_tree:

Self-hosted MCP Server registry for your private AI agents

MCPJungle is a single source-of-truth registry for all Model Context Protocol based Servers running in your Organisation.

🧑‍💻 Developers use it to register & manage MCP servers and the tools they provide from a central place.

🤖 AI Agents use it to discover and consume all these tools from a single MCP Server.

MCPJungle is the only MCP Server your agents need to connect to!

Who should use MCPJungle?

1. Devs using MCP Clients like Claude, Cursor, & Windsurf that need to connect to multiple MCP servers for calling tools.
2. Devs building AI Agents that need to access multiple MCP servers for calling tools.
3. Organisations who want to view and manage all their MCP servers from one centralized place. Secure & Private 🔒

Installation

[!WARNING] MCPJungle is BETA software.

We're actively working to make it production-ready. You can provide your feedback by starting a discussion in this repository.

MPCJungle is shipped as a stand-alone binary.

You can either download it from the Releases Page or use Homebrew to install it:

$ brew install mcpjungle/mcpjungle/mcpjungle

Verify your installation by running

$ mcpjungle version

[!IMPORTANT] On MacOS, you will have to use homebrew because the compiled binary is not Notarized yet.

Usage

MCPJungle has a Client-Server architecture and the binary lets you run both a Server and a Client.

Server

For running the MCPJungle server locally, docker compose is the recommended way:

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

Otherwise, you can run the server directly using the binary:

$ mcpjungle start

This starts the main registry server responsible for managing all MCP servers. It is accessible on port 8080 by default.

The server also exposes its own MCP server at /mcp for AI Agents to discover and call Tools provided by the registered MCP Servers.

It relies on a database and by default, creates a SQLite DB in the current working directory. Alternatively, you can supply a DSN for a Postgresql database to the server:

$ export DATABASE_URL=postgres://admin:root@localhost:5432/mcpjungle_db
$ mcpjungle start

If you use docker-compose, the DB is automatically created and managed for you.

Client

Once the server is up, you can use the CLI to interact with it.

Let's say you're already running a MCP server locally at http://127.0.0.1:8000/mcp which provides basic math tools like add, subtract, etc.

You can register this MCP server with MCPJungle:

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

If you used docker-compose to run the server, and you're not on Linux, you will have to use host.docker.internal instead of your local loopback address.

$ mcpjungle register --name calculator --description "Provides some basic math tools" --url http://host.docker.internal:8000/mcp

The registry will now start tracking this MCP server and load its tools.

Note: MCPJungle currently only supports MCP Servers using the Streamable HTTP Transport.

All tools provided by this server are now accessible via MCPJungle:

$ mcpjungle list tools

# Check tool usage
$ mcpjungle usage calculator/multiply

# Call a tool
$ mcpjungle invoke calculator/multiply --input '{"a": 100, "b": 50}'

[!NOTE] A tool in MCPJungle must be referred to by its canonical name which follows the pattern <mcp-server-name>/<tool-name>.

eg- If you register a MCP server github which provides a tool called git_commit, you can invoke it in MCPJungle using the name github/git_commit.

Your AI Agent must also use this canonical name to call the tool via MCPJungle.

Finally, you can remove a MCP server from the registry:

$ mcpjungle deregister calculator

After running this, the registry will stop tracking this server and its tools will no longer be available to use.

Cursor Configuration

Use the following configuration in Cursor to connect to MCPJungle:

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

(Assuming that MCPJungle is running on localhost:8080)

Authentication

MCPJungle currently supports authentication if your MCP Server accepts static tokens for auth.

This is useful when using SaaS-provided MCP Servers like HuggingFace, Stripe, etc. which require your API token for authentication.

You can supply your token while registering the MCP server:

# If you specify the `--bearer-token` flag, MCPJungle will add the `Authorization: Bearer <token>` header to all requests made to this MCP server.
$ mcpjungle register --name huggingface --description "HuggingFace MCP Server" --url https://huggingface.co/mcp --bearer-token <your-hf-api-token>

Support for Oauth flow is coming soon!

Development

This section contains notes for maintainers and contributors of MCPJungle.

Build for local testing

# Single binary for your current system
$ goreleaser build --single-target --clean --snapshot

# Test the full release assets (binaries, docker image) without publishing
goreleaser release --clean --snapshot --skip publish

# Binaries for all supported platforms
$ goreleaser release --snapshot --clean

Create a new release

1. Create a Git Tag with the new version

git tag -a v0.1.0 -m "Release version 0.1.0"
git push origin v0.1.0

2. Release

# Make sure GPG is present on your system and you have a default key which is added to Github.

# set your github access token
export GITHUB_TOKEN="<your GH token>"

goreleaser release --clean

This will create a new release under Releases and also make it available via Homebrew.