サポート エンジニアが同様の GitHub の問題を見つけてトラブルシューティングを迅速化するのに役立つ MCP サーバー。
依存関係をインストールします:
npm installGitHub トークンを環境変数として設定します。
export GITHUB_TOKEN=your_github_personal_access_tokenサーバーを構築します。
npm run buildclaude デスクトップ構成を更新します (例: code ~/Library/Application\ Support/Claude/claude_desktop_config.json
このリポジトリのクローン先の完全なパスを含めるように更新します。
{
"mcpServers": {
"find-similar-github-issues": {
"command": "node",
"args": [
"/Users/<repo_path>/build/index.js"
]
}
}
}Related MCP server: OSSInsight MCP Server
問題の説明に基づいて GitHub リポジトリ内の類似の問題を検索します
類似度スコアを計算して結果をランク付けします
リンク付きのフォーマットされた問題の詳細を返します
サーバーは次のツールを 1 つ提供します。
指定された説明に類似した GitHub の問題を検索します。
パラメータ:
owner : GitHubリポジトリの所有者/組織
repo : GitHubリポジトリ名
issueDescription : 類似の問題を見つけるための問題の説明
maxResults : 返される類似の問題の最大数（デフォルト: 5）
この実装では、テキストの比較に単純なJaccard類似度係数を使用しています。本番環境での使用においては、より高度なNLP技術を導入し、より正確な類似度マッチングを実現することをご検討ください。
Find GitHub issues similar to a new issue description
| Name | Required | Description | Default |
|---|---|---|---|
| issueDescription | Yes | Description of the issue to find similar ones for | |
| maxResults | No | Maximum number of similar issues to return | |
| owner | Yes | GitHub repository owner/organization | |
| repo | Yes | GitHub repository name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure but only states the basic function. It lacks details on how similarity is determined (e.g., semantic matching, keywords), performance characteristics (e.g., response time, rate limits), or error handling, leaving significant gaps for a tool with potential complexity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no wasted words, efficiently conveying the core purpose. It is appropriately sized and front-loaded, making it easy to understand at a glance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is insufficient for a tool that performs similarity matching—a non-trivial operation. It omits critical details like return format, matching algorithm, or error cases, leaving the agent with incomplete context for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the input schema fully documents all parameters. The description adds no additional meaning beyond what the schema provides, such as explaining the relationship between parameters or usage nuances, meeting the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Find') and resource ('GitHub issues similar to a new issue description'), making the purpose immediately understandable. However, without sibling tools for comparison, it cannot differentiate from alternatives, preventing a score of 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or contextual constraints. It simply restates the tool's function without offering usage instructions or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0find-similar-issuesScored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools, making disambiguation perfect. The tool's purpose is clearly defined and singular.
The single tool name follows a consistent verb-noun pattern (find-similar-issues), and with no other tools to compare, there is no inconsistency. The naming is clear and predictable.
A single tool is too few for a server named 'GitHub Support Assistant', which implies broader functionality beyond just finding similar issues. This minimal set feels thin and incomplete for the apparent scope.
The tool set is severely incomplete for the domain of GitHub support, lacking essential operations like creating issues, commenting, searching repositories, or managing pull requests. It covers only a narrow aspect, leading to dead ends for agents.
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
Finds real, maintained open-source repos that fit your project. MCP grounding for coding agents.
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals.
Ask any GitHub repository a question. Get source-backed answers.
