About Paul Walker's Bespoke MCP Tools
Paul Walker's Bespoke MCP Tools is a changing collection of one-off tools for agents and developers. It combines a task queue with background process controls and a timed wait tool.
Key features
- 01Add tasks to a queue
- 02Pop the next queued task
- 03Launch shell commands in background
- 04Read background process output
- 05Stop a running process
- 06Wait for a specified duration
Use cases
- 01Queue and retrieve tasks for an agent
- 02Run a shell command without blocking
- 03Check output or stop a background process
MCP support
The MCP server exposes task queue operations, background shell process controls, and a wait tool to connected MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEPaul Walker's Bespoke MCP Tools
A shifting selection of one-off MCP tools that pwalker is playing with.
Currently contains:
- push-tasks, which takes a task list and/or file containing newline-separate tasks and adds them to the queue
- pop-task, which pops one task from the queue or indicates the queue is empty
- launch-background-process, which launches a shell command in the background
- get-process-output, which gets the output of a previously launched process
- kill-process, which kills a previously launched process
- wait, which waits a specified number of seconds
Goose Installation
Use this extension installation link:
Or add to goose in Settings -> Extensions -> Add with this information:
- Type: Standard IO
- Command: `npx -y github:pauldw/pwalker-mcp"
- ID, Name, and Description: Anything you want.
Local Development
To run the MCP server from a local copy, use this MCP command instead:
npm --prefix /path/to/local/copy run start
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.