Development · MODEL CONTEXT PROTOCOL
msnidal yellhorn mcp
Yellhorn offers MCP tools to publish detailed workplans as GitHub issues with entire-codebase reasoning and to review diffs against them
WHAT IT CONNECTS
What msnidal yellhorn mcp gives an AI Agent
- **Create Workplans**: Creates detailed implementation plans based on a prompt and taking into consideration your entire codebase, posting them as GitHub issues and exposing them as MCP resources for your coding agent
- **Judge Code Diffs**: Provides a tool to evaluate git diffs against the original workplan with full codebase context and provides detailed feedback, ensuring the implementation does not deviate from the original requirements and providing guidance on what to change to do so
- **Seamless GitHub Integration**: Automatically creates labeled issues, posts judgement sub-issues with references to original workplan issues
- **Context Control**: Use `.yellhornignore` files to exclude specific files and directories from the AI context, similar to `.gitignore`
- **MCP Resources**: Exposes workplans as standard MCP resources for easy listing and retrieval
- `GEMINI_API_KEY`: Your Gemini API key (required for Gemini models)
- `OPENAI_API_KEY`: Your OpenAI API key (required for OpenAI models)
- `REPO_PATH`: Path to your repository (defaults to current directory)
- `YELLHORN_MCP_MODEL`: Model to use (defaults to "gemini-2.5-pro-preview-03-25"). Available options:
- Gemini models: "gemini-2.5-pro-preview-03-25", "gemini-2.5-flash-preview-04-17"
- OpenAI models: "gpt-4o", "gpt-4o-mini", "o4-mini", "o3"
- `title`: Title for the GitHub issue (will be used as issue title and header)
- `detailed_description`: Detailed description for the workplan
- `codebase_reasoning`: (optional) Control whether AI enhancement is performed:
- `"full"`: (default) Use AI to enhance the workplan with full codebase context
- `"lsp"`: Use AI with lightweight codebase context (function/method signatures, class attributes and struct fields for Python and Go)
- `"none"`: Skip AI enhancement, use the provided description as-is
- `debug`: (optional) If set to `true`, adds a comment to the issue with the full prompt used for generation
- JSON string containing:
- `issue_url`: URL to the created GitHub issue
- `issue_number`: The GitHub issue number
- `issue_number`: The GitHub issue number for the workplan.
- The content of the workplan issue as a string
- `issue_number`: The GitHub issue number for the workplan.
- `base_ref`: Base Git ref (commit SHA, branch name, tag) for comparison. Defaults to 'main'.
- `head_ref`: Head Git ref (commit SHA, branch name, tag) for comparison. Defaults to 'HEAD'.
- `codebase_reasoning`: (optional) Control which codebase context is provided:
- `"full"`: (default) Use full codebase context
- `"lsp"`: Use lighter codebase context (only function signatures for Python and Go, plus full diff files)
- `"none"`: Skip codebase context completely for fastest processing
- `debug`: (optional) If set to `true`, adds a comment to the sub-issue with the full prompt used for generation
- A confirmation message that the judgement task has been initiated
- `list-resources`: Lists all workplans (GitHub issues with the yellhorn-mcp label)
- `get-resource`: Retrieves the content of a specific workplan by issue number
- **Testing**: Runs automatically on pull requests and pushes to the main branch
- Linting with flake8
- Format checking with black
- Testing with pytest
- **Publishing**: Automatically publishes to PyPI when a version tag is pushed
- Tag must match the version in pyproject.toml (e.g., v0.2.2)
- Requires a PyPI API token stored as a GitHub repository secret (PYPI_API_TOKEN)
- Update version in pyproject.toml and yellhorn_mcp/\_\_init\_\_.py
- Update CHANGELOG.md with the new changes
- Commit changes: `git commit -am "Bump version to X.Y.Z"`
- Tag the commit: `git tag vX.Y.Z`
- Push changes and tag: `git push && git push --tags`
SECURITY
An MCP listing is not a security review
An MCP server may receive model context, credentials, local files, or permission to call external systems. Review its code, requested environment variables, network behavior, package provenance, and maintenance status before connecting it to an agent.