github-fetcher

GitHub repository search

github_search_repos

Read-onlyIdempotent

Search GitHub repositories with GitHub search syntax to locate projects by stars, forks, help-wanted issues, or update date. Sort, paginate, and filter public results.

Instructions

Search repositories by GitHub search syntax. Supports stars, forks, help-wanted-issues, and updated sorting.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "github_search_repos"
  }
}

Input Schema

Name	Required	Description
`page`	No	Page number, starting at 1
`sort`	No	Sort field
`fresh`	No	Bypass the local cache
`order`	No	Sort order
`query`	Yes	GitHub repository search query
`per_page`	No	Items per page, default 20
`public_only`	No	Drop private repositories from the results

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.2.1Nov 7, 2026

addedInput schema / properties / public_only

Added value: +{
+  "description": "Drop private repositories from the results",
+  "type": "boolean"
+}

First observedv0.1.0Nov 1, 2026

TDQS

B3.2/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered; the description adds nothing beyond that. It omits meaningful behavioral facts for a search tool, such as pagination limits, GitHub's result-cap behavior, or the presence of a local cache (only the 'fresh' param hints at it). The sorting sentence merely repeats the schema enum.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with the core purpose front-loaded, which is easy to scan. The second sentence is largely redundant with the 'sort' enum in the input schema, costing a small amount of space for no added information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a seven-parameter read-only search tool with no output schema and full schema descriptions, the definition covers the basics, and annotations handle safety. Gaps remain around result limits, rate limiting and the return shape (what fields a repository result contains), which matter for a search tool an agent will paginate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all seven parameters are already documented including the sort enum, order, page, per_page and public_only. The description's enumeration of sort values duplicates the schema rather than clarifying query syntax or how public_only interacts with authentication, so it adds little meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Search repositories') and names the query syntax, making it immediately identifiable as a repo search. However, it never distinguishes itself from sibling search tools such as github_search_code or github_search_issues, leaving the agent to infer the boundary from the name alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the verb 'search' plus mention of GitHub search syntax; there is no explicit when-to-use statement, no note about when to prefer a code or issue search, and no prerequisites. The agent must infer that this is the correct tool for finding repositories.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.