EnigmaPython MCP

An MCP (Model Context Protocol) server that brings the capabilities of the enigmapython library to LLMs, allowing them to encrypt and decrypt messages using historically accurate Enigma machine emulators

An MCP (Model Context Protocol) server that brings the capabilities of theenigmapythonlibrary to LLMs, allowing them to encrypt and decrypt messages using historically accurate Enigma machine emulators.

This MCP Server is listed onGlama.aiwith this score

- machine_model(str): Model name. Supported:'M3','M4','I','I_Norway','I_Sondermaschine','K','K_Swiss','D','Z','B_A133','T'.
- message(str): The plaintext or ciphertext to process.
- rotors(list[object]): List ofRotorConfigobjects. Each object specifiesrotor_type(str),ring_setting(int, default=0), andinitial_position(int | str, default=0). IMPORTANT: The list MUST be ordered exactly as:[Fastest/Rightmost, Middle, Slowest/Leftmost, Greek (if M4)].
- reflector(object): AReflectorConfigobject specifyingreflector_type(str), and optionallyring_setting(int) andinitial_position(int | str) for rotating reflectors.
- plugboard_pairs(dict, optional): Dictionary mapping plugboard connections (e.g.,{"A": "B", "C": "D"}).

(Alternatively, you can just runuvx enigmapython-mcpif you haveuvinstalled!)

enigmapython-mcp --transport sse --host 0.0.0.0 --port 8000

docker run -p 8000:8000 enigmapython-mcp --transport sse --host 0.0.0.0 --port 8000

We provide two distinctmcpbbundles for 1-click installation on Claude Desktop. Simply download your preferred bundle from the GitHub Releases page and drag-and-drop it into Claude Desktop's Extensions menu:
- enigmapython-mcp-docker.mcpb: Extremely lightweight, relies on your local Docker daemon to run the server in an isolated container.(Recommended)
- enigmapython-mcp-python.mcpb: Contains the full Python source. Claude Desktop will natively build a virtual environment and run the server without needing Docker.

If you prefer manual configuration viaclaude_desktop_config.json, use the settings below:

{ "mcpServers": { "enigma": { "command": "uvx", "args": ["enigmapython-mcp", "--transport", "stdio"] } } }

(Note: Make sure you have built the Docker image first:docker build -t enigmapython-mcp .)

{ "mcpServers": { "enigma": { "command": "docker", "args": ["run", "-i", "--rm", "enigmapython-mcp"] } } }

To use this server with OpenCode, add the following to your~/.config/opencode/opencode.json(global) oropencode.json(project-level) under themcpsection:

{ "mcp": { "enigma": { "type": "local", "command": [ "uvx", "enigmapython-mcp", "--transport", "stdio" ], "enabled": true } } }

(Note: Make sure you have built the Docker image first:docker build -t enigmapython-mcp .)

{ "mcp": { "enigma": { "type": "local", "command": [ "docker", "run", "-i", "--rm", "enigmapython-mcp" ], "enabled": true } } }

Once the server is configured, you can test it by sending the following prompts to your LLM:

"I need to encrypt the message 'TOPSECRET' using an Enigma M3. The rotors, ordered from fastest to slowest, are III, II, and I. All starting at position 0 with ring settings at 0. Use reflector 'UKWB' and no plugboard. What is the ciphertext?"

Example 2: Historical Decryption (Enigma I)

"Decrypt this 1930 Enigma I message. The ciphertext is 'GCDSEAHUGWTQGRK'. The machine settings, strictly ordered from Fastest to Slowest, are: Rotors III, I, and II. Their respective ring settings are 21, 12, and 23. Their initial positions are 11, 1, and 0. The reflector is 'UKWA'. The plugboard swaps are: A/M, F/I, N/V, P/S, T/U, W/Z."

"Use the Enigma M4 to encrypt the message 'DIVE DIVE DIVE'. The machine uses the 'UKWBThin' reflector. The rotors, explicitly ordered as [Fastest, Middle, Slowest, Greek], are: VIII (pos 2), III (pos 6), IV (pos 12), and Gamma (pos 21). All ring settings are 0. Please process this."

A comprehensive test suite is included intests/test_server.py. It tests the encryption and decryption reversibility for all 10 supported Enigma models.

# Activate your virtual environment first source .venv/bin/activate pip install pytest export PYTHONPATH=$PYTHONPATH:$(pwd)/src/enigmapython_mcp && pytest tests/*

Because the Model Context Protocol requires a stateful initialization handshake before any tools can be called, manually testing the SSE endpoint withcurlis quite complex.

The easiest and officially recommended way to test the server is using theMCP Inspector:
- Ensure your server is running in SSE mode:

uv run enigmapython-mcp --transport sse --host 0.0.0.0 --port 8000

3 tools for global censorship intelligence (119 countries) + E2E encrypted agent-to-agent messaging with Double Ratchet and post-quantum crypto

Agent-native forum for the x402/A2A ecosystem. The hosted MCP server exposes the whole forum as tools — threads, comments, votes, USDC bounties (Coinbase x402 on Base), provider reviews, and search. Endpoint: https://api.achivx.com/mcp/ (HTTP, OAuth 2.1).

Encrypted file transfer and communication between AI agents - send and receive files securely with E2E encryption, agent identity, and trust scoring.

Real SIM-backed mobile numbers for AI agents. Provision phone numbers, receive SMS, and capture OTP codes — bypasses VoIP blocks that reject Twilio/Vonage. 5 tools: provision_number, wait_for_otp, get_messages, release_number, list_numbers.

Create, edit, and delete email aliases and manage encrypted file shares with anon.li MCP.

MCP server for end-to-end encrypted, on-chain agent-to-agent messaging on COTI, with native-token rewards and starter grants. Built on Garbled Circuits. 18 tools, open source.

Broadcast AI-driven alerts securely to thousands of phones and laptops in seconds—no apps, no SMS, and total user privacy.

Voice MCP server: voice-cloning TTS/STT with speak, talk, voice inbox and feeds - remote MCP with OAuth at mcp.koe.live

Telegram MCP server using User API (MTProto) with default-deny ACL, granular per-chat permissions, file sending, media downloads, and rate limiting

Overlay network for AI agents: permanent virtual address, encrypted UDP tunnels, NAT traversal, trust handshakes, and an app store of installable agent capabilities.