A FastAPI-based MCP server that integrates with GitHub via the GitHub MCP server to provide repository analysis, commit history, contributor information, and AI-powered chat capabilities for GitHub repositories
This server has significant definition quality gaps. Tool descriptions are present but generic (avg ~80 chars, below the 194-char baseline). Most critically, 4 of 9 tools lack visible input schemas in the provided source code (chat, list_repositories, analyze_repository, chat_repository, chat_with_repo, generate_summary). Parameter descriptions are minimal or absent. No output schemas documented. Error handling is not evident. The server exposes github_token as a parameter in multiple tools (chat, chat_with_repo, generate_summary), violating secret-injection patterns. Tool naming is reasonable (verb_noun style) but composition is poor, multiple chat tools (chat, chat_repository, chat_with_repo) do similar things without clear differentiation.
Analyze a repository and provide overall code quality score, key insights about the codebase, areas for improvement, and recent changes and their impact
Process a natural language query about a GitHub repository using an AI agent
Answer questions about a specific GitHub repository using an AI agent
Chat with an AI agent about repositories using GitHub MCP server integration
Count how many repositories the authenticated user has
Generate a commit summary across all repositories accessible with the GitHub token, including total commits, top repositories, top contributors, and recent activity
Missing input schemas for 6 tools (chat, list_repositories, analyze_repository, chat_repository, chat_with_repo, generate_summary). Cannot verify parameter types or constraints.
GitHub tokens exposed as tool parameters (chat, chat_with_repo, generate_summary). Violates secret-injection pattern, credentials in params leak into logs and traces.
Three chat tools (chat, chat_repository, chat_with_repo) with overlapping functionality and unclear differentiation. LLMs will struggle to select the correct one.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 47 | 2026-07-28+ | v2 |
Fetch the commit history for a specified user in a specified repository
List the contributors in a specified repository
List all repositories the authenticated user has access to, formatted as JSON with owner and name fields, sorted by last modified date, limited to 10 repositories
No output schemas documented for any tool. LLMs cannot plan downstream calls or extract structured data reliably.
No error handling guidance. Tools do not indicate what to do on failure (retry, ask user, fatal).