@msnidal
基本信息
Yellhorn offers MCP tools to publish detailed workplans as GitHub issues with entire-codebase reasoning and to review diffs against them
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"yellhorn-mcp": {
"command": "uv",
"args": [
"sync",
"--group",
"dev"
]
}
}
}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。
Yellhorn MCP is a Model Context Protocol server that creates detailed workplans for implementing tasks or features. It uses large AI models (e.g., Gemini 2.5 Pro, GPT‑5, o3, Grok‑4) with full codebase context, URL access, and optional web search. The server is designed for coding agents like Claude Code to define work, and later to review the output against the original requirements.
Install via uv sync --group dev or uv pip install yellhorn-mcp. Set environment variables GEMINI_API_KEY, OPENAI_API_KEY, XAI_API_KEY, REPO_PATH, and optionally YELLHORN_MCP_MODEL and YELLHORN_MCP_SEARCH. The GitHub CLI (gh) must be installed and authenticated. Configure the server in your MCP client (Codex CLI, VSCode/Cursor, or Claude Code) using a config.toml or mcp.json file with command uv run yellhorn-mcp.
.yellhornignore file to exclude files from AI contextIt supports Gemini (2.5‑pro, 2.5‑flash, 2.5‑flash‑lite), OpenAI (GPT‑4o, GPT‑4o‑mini, o4‑mini, o3, GPT‑4.1, GPT‑5 series), and xAI Grok (Grok‑4, Grok‑4 Fast) models. Deep Research models (o3‑deep‑research, o4‑mini‑deep‑research, GPT‑5) enable web search and code interpreter tools.
Create a `.yellhornignore` file in your repository, similar to `.gitignore`. The server also provides the `curate_context` tool to generate a `.yellhorncontext` whitelist that further reduces token usage.
You need API keys for the models you plan to use (Gemini, OpenAI, or xAI), the GitHub CLI (`gh`) installed and authenticated, and a Python environment managed by `uv`. The repository to analyze must be accessible via `REPO_PATH`.
Yes. Set the environment variable `YELLHORN_MCP_SEARCH` to `"off"` (default is `"on"` for Gemini models). You can also pass `disable_search_grounding: true` to individual tool calls.
The `judge_workplan` tool compares two git refs (base and head) against a workplan stored in a GitHub issue. It creates a sub‑issue, then asynchronously evaluates the diff with full codebase context and posts detailed feedback.
A Model Context Protocol (MCP) server that helps read GitHub repository structure and important files.
a private MCP server for accessing Linear
Model Context Protocol Servers
A GitHub MCP Server extension for Zed
MCP servers for the Atlassian products (Bitbucket, Confluence, JIRA) of the Data Center version
评论