GitMCP is a tool that allows you to get the documentation for a given repository.
GitMCP has 4 tools with basic descriptions but significant gaps in schema completeness and parameter documentation. Tool names follow verb_noun convention (fetch_*, search_*), which is good. However, input schemas are minimal or missing type information. fetch_documentation has NO input parameters documented despite being a tool. Descriptions are present but generic (avg ~80 chars), lacking WHEN to use guidance and dependency hints. No output schemas documented. Error handling and recovery guidance absent. No tool annotations (readOnlyHint). This is a typical community-grade server with foundational issues.
Fetch documentation for the repository
Generic tool to fetch content from any absolute URL, respecting robots.txt rules. Use this to retrieve referenced urls (absolute urls) that were mentioned in previously fetched documentation.
Search repository code
Search repository documentation
fetch_documentation has no input schema, tool definition is incomplete. Cannot determine if parameters are required or optional.
No output schemas documented for any tool. LLMs cannot plan downstream calls or extract required fields (e.g., does search_code return file paths, line numbers, both?).
Descriptions lack WHEN-to-use guidance and dependency hints. E.g., search_code description does not explain when to call it vs search_documentation, or whether it requires a repository context.
search_code 'page' parameter lacks min/max bounds. Unbounded pagination invites LLMs to pass absurd page numbers.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 53 | 2026-07-28+ | v2 |
No error handling or recovery guidance. Tools do not document what happens on invalid URL, missing repository, or API failures.