commands-mcp
An MCP server that lets you define and run custom shell commands via YAML templates, with built-in tools for flashing and serial communication in embedded development.
README
commands-mcp 
Build MCP Server with command template.
Usage
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"commands": {
"command": "/path/to/commands-mcp",
"args": [
"/path/to/your/project"
]
}
}
}
Example
A commands.yaml file should be placed in the root of your project. Here's an example:
# yaml-language-server: $schema=https://listenai.github.io/commands-mcp/schema/master/commands.json
commands:
zephyr_build:
description: Build the specified Zephyr application
args:
- name: board
description: |
The board identifier to build for. If it can't be determined from the
context, it should be prompted for.
required: true
- name: source_dir
description: |
Path to the source directory of the Zephyr application to build.
Defaults to the current working directory.
default: .
- name: pristine
description: |
If true, the build directory will be cleaned before building.
default: false
command: |
source .venv/bin/activate
west build -b {{board}} -s {{source_dir}} {{#if pristine}}--pristine{{/if}}
For code completion on the commands.yaml file, redhat.vscode-yaml extension is recommended.
The commands.yaml file
commands: The root key for command definitions.<tool>: A tool named<tool>.description: A description of what the command does.args: A list of arguments for the command, if any.name: The name of the argument.description: A description of the argument.type: The type of the argument (optional, acceptsstring,number,boolean, defaults tostring).required: Whether the argument is required (defaults tofalse).default: The default value for the argument, if it is not required.
command: The command to run. Supports Handlebars templating for arguments.shell: The shell used to execute the command. Defaults to "bash" on Unix-like systems and "powershell" on Windows. Also supports "python" for using Python script in the command.venv: Optional path to a Python virtual environment to use. If specified, the command will be executed with the specified venv activated.
Python support
If the shell is set to python, the command will be executed using Python. If a virtual environment is specified in the venv field, it will be activated before executing the command.
commands:
some_python_script:
description: A python script that does something
shell: python
venv: .venv
command: |
import sys
print(f"Running Python {sys.version} in virtual environment {sys.prefix}")
Built-in tools
In addition to the commands defined in commands.yaml, the MCP Server provides several built-in tools, which can be enabled in the commands.yaml file with corresponding configuration.
Flash tools
Built-in tools for flashing firmware to LISTENAI devices.
flash:
enabled: true # Enable flash tools
chip: mars # Chip model, can be '6', 'mars'
baudrate: 1500000 # Baud rate for flashing, defaults to 1500000
Serial tools
Built-in tools for reading logs from connected serial devices.
serial:
enabled: true # Enable serial tools
baudrate: 115200 # Baud rate for serial communication, defaults to 115200
reset: dtr # Method to reset the device before reading logs, can be
# 'dtr' or 'rts'. If not specified, no reset will be performed.
reset_interval: 100 # Interval in milliseconds between the reset line is
# asserted and deasserted, defaults to 100ms.
Schematic tools
Built-in tools to help the AI better understand the hardware schematic of the board. For details about the schematic files, see the Schematic.
schematic:
enabled: true # Enable schematic tools
board: csk6_duomotai_devkit # Board name, should match the board file defined
# in `boards_dir`.
socs_dir: schematic/socs # Directory containing SoC-level schematic
# definitions. Defaults to "schematic/socs".
boards_dir: schematic/boards # Directory containing board-level schematic
# definitions. Defaults to "schematic/boards".
License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.