What prerequisites are needed to run gotask-mcp?
You need `uv` (e.g., `brew install uv`) and `Taskfile` (e.g., `brew install go-task`) installed on your system.
@PaddyAlton
基本信息
A Model Context Protocol (MCP) Server for go-task (
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
gotask-mcp is a Model Context Protocol (MCP) server that integrates with Taskfile (go-task), a task runner. It enables AI coding agents to retrieve a list of available tasks and execute them, making regular development workflows like autofixes and QA checks accessible to LLM-driven tools.
Install the prerequisites uv and Taskfile (e.g., via Homebrew). Clone the repository and ensure a Taskfile.yml exists in your working project. In Cursor IDE settings > MCP Servers, start a server with the command:
uv run --with mcp --directory /path/to/gotask-mcp mcp run /path/to/gotask-mcp/src/server.py
Optionally copy the included .cursor/rules/tool-use-rule.mdc into your project to guide the agent.
Taskfile.ymlYou need `uv` (e.g., `brew install uv`) and `Taskfile` (e.g., `brew install go-task`) installed on your system.
Tasks are defined in a `Taskfile.yml` file located in the working project directory. The server reads that file using the working directory path provided by the client.
The client (e.g., Cursor IDE Agent) passes the working directory path as an input to the tools, allowing the server to locate and read the correct `Taskfile.yml`.
At the time of writing, MCP resources do not work well with Cursor IDE. Therefore the list-tasks feature is implemented as a tool rather than a resource.
The server is started via the `mcp` CLI using `mcp run`, which by default uses stdio transport for communication with the client.
Painless E2E Automation for Mobile and Web

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Hindsight: Agent Memory That Learns
评论