Tools
Tools are for LLMs to request, i.e. Claude Desktop app. Claude Sonnet 3.5 intelligently uses both tools, I was pleasantly surprised.
run_command- run a command, i.e.hostnameorls -alorecho "hello world"etc
run_script- run a script! (i.e.fish,bash,zsh,python)
[!WARNING] Be careful what you ask this server to run! In Claude Desktop app, useApprove Once(notAllow for This Chat) so you can review each command, useDenyif you don't trust the command. Permissions are dictated by the user that runs the server. DO NOT run withsudo.
Video walkthrough
<a href="https://youtu.be/0-VPu1Pc18w"><img src="https://img.youtube.com/vi/0-VPu1Pc18w/maxresdefault.jpg" width="480" alt="YouTube Thumbnail"></a>
Prompts
Prompts are for users to include in chat history, i.e. via
Zed's slash commands (in its AI Chat panel)run_command- generate a prompt message with the command output
Development
Install dependencies:
Build the server:
For development with auto-rebuild:
Installation
To use with Claude Desktop, add the server config:
On MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.jsonUse the published npm package
Published to npm as mcp-server-commands using this workflow
Use a local build (repo checkout)
Logging
Claude Desktop app writes logs to
~/Library/Logs/Claude/mcp-server-mcp-server-commands.logBy default, only important messages are logged (i.e. errors).
If you want to see more messages, add
--verbose to the args when configuring the server.By the way, logs are written to
STDERR because that is what Claude Desktop routes to the log files.
In the future, I expect well formatted log messages to be written over the STDIO transport to the MCP client (note: not Claude Desktop app).Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
The Inspector will provide a URL to access debugging tools in your browser.
Tools
Tools are for LLMs to request, i.e. Claude Desktop app. Claude Sonnet 3.5 intelligently uses both tools, I was pleasantly surprised.
run_command- run a command, i.e.hostnameorls -alorecho "hello world"etc
run_script- run a script! (i.e.fish,bash,zsh,python)
[!WARNING] Be careful what you ask this server to run! In Claude Desktop app, useApprove Once(notAllow for This Chat) so you can review each command, useDenyif you don't trust the command. Permissions are dictated by the user that runs the server. DO NOT run withsudo.
Video walkthrough
<a href="https://youtu.be/0-VPu1Pc18w"><img src="https://img.youtube.com/vi/0-VPu1Pc18w/maxresdefault.jpg" width="480" alt="YouTube Thumbnail"></a>
Prompts
Prompts are for users to include in chat history, i.e. via
Zed's slash commands (in its AI Chat panel)run_command- generate a prompt message with the command output
Development
Install dependencies:
Build the server:
For development with auto-rebuild:
Installation
To use with Claude Desktop, add the server config:
On MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.jsonUse the published npm package
Published to npm as mcp-server-commands using this workflow
Use a local build (repo checkout)
Logging
Claude Desktop app writes logs to
~/Library/Logs/Claude/mcp-server-mcp-server-commands.logBy default, only important messages are logged (i.e. errors).
If you want to see more messages, add
--verbose to the args when configuring the server.By the way, logs are written to
STDERR because that is what Claude Desktop routes to the log files.
In the future, I expect well formatted log messages to be written over the STDIO transport to the MCP client (note: not Claude Desktop app).Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
The Inspector will provide a URL to access debugging tools in your browser.