Meshtastic-MCP: AI Tooling for Meshtastic Device Control and Testing
This repository profile is provided by osrepos.com, an open source repository discovery platform.

Summary
Meshtastic-MCP provides an MCP server and agent skills designed for AI tooling to discover, drive, observe, and test Meshtastic devices and applications. It offers a comprehensive suite of capabilities, from portable device control to advanced hardware-free end-to-end testing and replay functionalities. This project aims to streamline the development and testing of Meshtastic ecosystems.
Repository Information
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
Meshtastic-MCP is a powerful Python project designed to provide an MCP (Model Context Protocol) server and a suite of agent skills for interacting with Meshtastic devices and applications. It enables AI tooling to seamlessly discover, drive, observe, and test Meshtastic ecosystems, offering a robust framework for automation and development.
Why Use It and Key Features
This repository is crucial for anyone looking to automate or deeply test Meshtastic setups, especially with AI integration. It offers a comprehensive set of capabilities:
- AI-Driven Device Control and Testing: Meshtastic-MCP allows AI agents to perform closed-loop device and app end-to-end testing, streamlining development workflows.
- Portable Core: Works with any connected Meshtastic device, supporting serial and TCP connections for basic operations like discovery, device information, sending messages, and recording data, without requiring firmware checkouts.
- Firmware Management: Integrates with PlatformIO to build, clean, flash, and perform OTA updates for Meshtastic firmware.
- Hardware-Free End-to-End Testing: Orchestrates Android emulators and iOS simulators for comprehensive testing of Meshtastic apps without physical hardware.
- RF Compliance with SDR: Utilizes SDR dongles for RF compliance checks, including occupancy scans and on-air TX verification.
- Local Model Integration: Offloads token-heavy tasks like summarizing recorder windows or triaging e2e failures to local GPUs via Ollama or OpenAI-compatible servers.
- Replay Functionality: Simulates Meshtastic devices by serving captured mesh data over TCP, allowing for reproducible app/UI development and testing with fully controllable, synthetic meshes.
- FleetSuite Web Control Plane: Provides a local web UI for managing a multi-board hardware bench, offering live device registry, build queues, flashing, recovery, and camera streams for screen assertions.
- Hardware Test Suite: Includes a tiered pytest suite for unit, mesh, telemetry, and recovery tests, supporting various Meshtastic boards on a USB-hub bench.
- Decoupled Design: Extracted from the main Meshtastic firmware repository, it can be installed and distributed independently, with firmware-build tools activating only when a firmware checkout is present.
Installation
To get started with Meshtastic-MCP, you can install it using uv (recommended) or pipx.
First, install the CLI and MCP server:
# Install the CLI + MCP server (uv recommended; also works with pipx)
uv tool install 'meshtastic-mcp[ui]' # includes camera/OCR support
# or without UI extras:
uv tool install meshtastic-mcp
Then, register the server with your MCP client and install the bundled skills:
meshtastic-mcp install # claude-code user scope; --client cursor|windsurf|claude-desktop
Examples
Here are some quick examples to demonstrate how to use Meshtastic-MCP:
Check available components and dependencies:
uvx meshtastic-mcp doctor # check what's available
Inside an MCP client like Claude Code, you can interact with your Meshtastic devices:
list_devices() # find your device port
device_info(port="/dev/cu.usbmodem101") # firmware, region, node count
list_nodes(port="/dev/cu.usbmodem101") # mesh peers
send_text(port="/dev/cu.usbmodem101", text="hello mesh")
packets_window(port="/dev/cu.usbmodem101", start="-30s") # confirm TX packet
Links
- GitHub Repository: meshtastic/meshtastic-mcp
Related repositories
Similar repositories that may be relevant next.
AutoResearch: AI/ML Research Agents from Idea to Paper-Ready Evidence
September 22, 2026
AutoResearch is an open-source agent workflow designed for AI and machine learning research. It automates the entire research process, from generating ideas and planning experiments to execution, analysis, and independent evaluation. This project helps researchers produce paper-ready evidence efficiently and with traceable provenance.
HarnessRouter: Unified Interface for AI Agent Harnesses
September 22, 2026
HarnessRouter Community Edition provides a self-hosted, Apache-2.0 licensed unified interface for various AI agent harnesses like Codex, Claude Code, and Hermes. It allows users to run multiple agents through a single API, offering features such as sessions, streaming, file handling, and cancellation. The project implements the open-standard Unified Harness Protocol (UHP), ensuring users maintain control over their keys and infrastructure.

AREX-Skill: A Skill Library for Automated Machine Learning and Auto-Research
September 21, 2026
AREX-Skill is a powerful skill library designed to advance automated machine learning and auto-research. It distills over 5,000 executable skills from more than 1,000 popular GitHub repositories, making complex ML knowledge directly usable by coding agents. This project significantly enhances agent performance in various research tasks by providing structured, validated operating knowledge.

oh-my-hermes: Enhance Hermes Agent with Advanced AI Workflow and Memory
September 17, 2026
oh-my-hermes is an all-in-one plugin designed to significantly enhance the Hermes Agent. It provides advanced coding intelligence, a robust long-term memory system, and optimized workflow packages, transforming standard Hermes requests into structured, actionable tasks with clear operational layers.
Source repository
Open the original repository on GitHub.