Skip to main content

mcpjungle

cmdop — messenger for AI agents

Installer for the cmdop CLI — stop keeping a directory of endpoints in your head.

pip install mcpjungle
mcpjungle

That's it. mcpjungle detects your platform, downloads the cmdop binary, verifies it against the published checksums, installs it, and hands over.

Not affiliated with the MCPJungle project. If you are looking for github.com/mcpjungle/MCPJungle, that is a different project — this package will not install it. This package is published by CMDOP and installs the cmdop CLI.

Anyone running more than three machines ends up maintaining a private index: which host has the GPU, which one has the database, which SSH alias still works. The index lives in your head and goes stale quietly.

cmdop replaces it with something you can address by name. One binary per machine, one place to talk to all of them. This package installs that binary.

How does CMDOP compare? CMDOP Skills vs OpenClaw: two approaches to AI agent skills →

Naming a machine beats remembering its address

Machines join a fleet and get a name. What changes is not the connection — it is that you stop needing to recall how to make one before you can ask a question.

The agent runs where the work is, with the files and credentials already on that box. Nothing is uploaded anywhere to make it reachable.

What is cmdop

One executable that is the agent, the relay, the local server and the web console at once. There is no gateway, backend, database server or broker to stand up — you add one binary to a machine you already own.

  • run an AI agent on your own machine, with your own tools
  • reach it from anywhere: terminal, files, remote execution
  • connect machines into a fleet
  • works with Claude Code and other agent engines under the hood

Full documentation: docs.cmdop.com

Usage

mcpjungle                    # install cmdop (if needed), then run it
mcpjungle --install-only     # install, don't hand over
mcpjungle --prefix ~/bin     # choose the install directory
mcpjungle --force            # reinstall even if already present
mcpjungle --quiet            # print only the installed path
mcpjungle -- --help          # everything after `--` goes to cmdop

Default install directory is ~/.local/bin (%LOCALAPPDATA%\cmdop\bin on Windows). No sudo, no system directories.

What it does, precisely

  1. Detects your OS and architecture.
  2. Fetches SHA256SUMS from install.cmdop.com.
  3. Downloads the matching binary to a temporary file.
  4. Verifies the SHA-256 against the published checksum. On mismatch it aborts and installs nothing.
  5. Moves the verified binary into the install directory and marks it executable.
  6. Runs it.

Supported: macOS (Apple Silicon, Intel), Linux (x64, arm64), Windows (x64).

What it does not do

  • No side effects at install time. pip install mcpjungle only unpacks files. Nothing is downloaded or executed until you run mcpjungle.
  • No network access on import. import mcpjungle touches nothing.
  • No telemetry. The package sends no analytics, ever.
  • No dependencies. Standard library only, so there is nothing to conflict with what you already have installed.

Python API

The installer is importable if you would rather script it:

import mcpjungle

target = mcpjungle.detect()
print(target.label, target.asset)

result = mcpjungle.install()
print(result.path, result.sha256)

mcpjungle.install() raises mcpjungle.InstallError with a user-facing message on any failure, and mcpjungle.UnsupportedPlatform when there is no published binary for the current machine.

Links

License

MIT

Metadata

Release files for mcpjungle 1.0.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mcpjungle 1.0.0
File Size Uploaded
mcpjungle-1.0.0.tar.gz 9.3 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for mcpjungle 1.0.0
File Interpreter ABI Platform
mcpjungle-1.0.0-py3-none-any.whl Python 3 none any Details

Total release size: 19.6 kB

Release files / mcpjungle-1.0.0.tar.gz

Download URL mcpjungle-1.0.0.tar.gz
Size 9.3 kB
Tags Source
SHA-256 checksum
How to use checksums
9e1a9186429efeba3e16ecba54f52e91ae203312ec0e9e848cd035fc77dcfc63
BLAKE2b-256 checksum
How to use checksums
dd4e8e697bcd8fa44f76ac8d44aee33556d6108ec6d5a54379f846f4b17fa5df
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.2

Release files / mcpjungle-1.0.0-py3-none-any.whl

Download URL mcpjungle-1.0.0-py3-none-any.whl
Size 10.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
1d862dd3ad9a5d4e2cad30936176add696ffcc5a5dbf087a5aaecf2ea6cf99e4
BLAKE2b-256 checksum
How to use checksums
6a5e520acb13c98e0bb808fce375223febf481f839387b83672e24565eee4f8d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.2

Release history Release notifications | RSS feed

This release

1.0.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page