Skip to main content

jmri-mcp

MCP (Model Context Protocol) server for JMRI — control your DCC model railroad by voice or chat, through any MCP client: Claude Desktop, Claude Code, xiaozhi voice assistants, etc.

pip install jmri-mcp

See the project repository for full documentation, including docs/llm-setup-claude.md and docs/llm-setup-xiaozhi.md for wiring this server into Claude Desktop/Code or xiaozhi/Kira.

Looking for a plain terminal client instead? See jmri-cli.

Third-party code

This package includes xiaozhi_wrapper, adapted from the MCP pipe example in xiaozhi-esp32 (MIT License, Copyright (c) 2025 Shenzhen Xinzhi Future Technology Co., Ltd. and Project Contributors) — see src/xiaozhi_wrapper/__init__.py's module docstring (inside this package) for the full notice.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

jmri_mcp-1.1.0.tar.gz (700.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

jmri_mcp-1.1.0-py3-none-any.whl (69.2 kB view details)

Uploaded Python 3

File details

Details for the file jmri_mcp-1.1.0.tar.gz.

File metadata

  • Download URL: jmri_mcp-1.1.0.tar.gz
  • Upload date:
  • Size: 700.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.20

File hashes

Hashes for jmri_mcp-1.1.0.tar.gz
Algorithm Hash digest
SHA256 2123dd22a3a44fbc5b08139bd16a508ca7e9c6edfff203929d12dc2e99e28047
MD5 3c177ec8d036cea22668d4fe1180f594
BLAKE2b-256 a5b554368395360684a4ff77c5f3ebbb8b9b0f7e8db66eb63caed38c13934129

See more details on using hashes here.

File details

Details for the file jmri_mcp-1.1.0-py3-none-any.whl.

File metadata

  • Download URL: jmri_mcp-1.1.0-py3-none-any.whl
  • Upload date:
  • Size: 69.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.20

File hashes

Hashes for jmri_mcp-1.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 fdf58a7c08247a76721f59ec654dd6f3561536a19a2e1b912f93ba63c712f5d0
MD5 09c925310dd98f83b90758509b57c5de
BLAKE2b-256 3e4aff618de65a8a78a4f4580d12ff32bcd469da7327b0c7fa4d50dc95df9114

See more details on using hashes here.

Release history Release notifications | RSS feed

1.3.0

2 files

1.2.0

2 files

This release

1.1.0 This release

2 files

1.0.0

2 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