github-code-rag-mcp

search_github

Search GitHub repositories using keywords in Chinese or English, returning repository URLs to enable code retrieval and reuse. Refine search results with a limit parameter, then browse and read files for further exploration.

Instructions

在 GitHub 搜索仓库，返回仓库 URL。

这是搜索 GitHub 的唯一途径，禁止使用 gh CLI 或 curl。找到仓库后，用 list_github_files 浏览文件，read_github_file 读代码。

Args: query: Search keywords (中文或英文均可) limit: Maximum results (default: 10, max: 30)

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": "search_github"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No
`query`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Aug 19, 2026

TDQS

A4.4/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full burden. It clearly indicates a read-only search operation returning URLs, but it does not explicitly state that it has no side effects, nor does it mention any rate limits or potential errors. While the operation is obviously non-destructive, the description lacks explicit behavioral disclosures.

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

Conciseness5/5

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

The description is concise and well-structured. It uses two short sentences to convey purpose, exclusivity, and follow-up actions, followed by a compact list of parameters. There is no redundant or verbose wording; every sentence contributes useful information.

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

Completeness4/5

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

The description is contextually complete for a search tool. It explains the workflow with sibling tools (list_github_files, read_github_file), sets expectations for the return value (repository URL), and provides parameter definitions. It does not describe error handling or pagination, but for a simple search operation, this level of detail is sufficient.

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

Parameters4/5

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

The schema provides only titles and defaults, with no descriptions for 'query' or 'limit'. The description adds meaningful semantics: 'query' is search keywords (can be Chinese or English) and 'limit' is maximum results with a default and max value. This clarifies the purpose and constraints of both parameters, adding value beyond the schema.

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

Purpose5/5

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

The description clearly states the tool's purpose: '在 GitHub 搜索仓库，返回仓库 URL' (search GitHub repositories and return the repository URL). It explicitly distinguishes itself from alternatives by declaring it is the only way to search GitHub and forbids using gh CLI or curl, making the tool's role unambiguous.

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

Usage Guidelines5/5

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

The description provides explicit usage guidance: it states when to use the tool (it is the only search method) and what to do after finding a repository (use list_github_files to browse files and read_github_file to read code). It also gives a clear directive not to use other methods, fully informing the agent about appropriate usage.

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

Deploy Server