엔지니어가 유사한 GitHub 문제를 찾아 문제 해결 속도를 높이는 데 도움이 되는 MCP 서버입니다.
종속성 설치:
지엑스피1
GitHub 토큰을 환경 변수로 설정하세요.
export GITHUB_TOKEN=your_github_personal_access_token서버를 빌드하세요:
npm run buildClaude 데스크탑 구성을 업데이트합니다(예: code ~/Library/Application\ Support/Claude/claude_desktop_config.json
이 저장소가 복제된 전체 경로를 포함하도록 업데이트합니다.
{
"mcpServers": {
"find-similar-github-issues": {
"command": "node",
"args": [
"/Users/<repo_path>/build/index.js"
]
}
}
}Related MCP server: OSSInsight MCP Server
문제 설명을 기반으로 GitHub 저장소에서 유사한 문제 검색
유사성 점수를 계산하여 결과를 순위화합니다.
링크가 포함된 형식화된 문제 세부 정보를 반환합니다.
서버는 하나의 도구를 제공합니다.
주어진 설명과 유사한 GitHub 문제를 찾습니다.
매개변수:
owner : GitHub 저장소 소유자/조직
repo : GitHub 저장소 이름
issueDescription : 유사한 문제를 찾기 위한 문제 설명
maxResults : 반환할 유사한 문제의 최대 개수(기본값: 5)
이 구현은 간단한 Jaccard 유사도 계수를 사용하여 텍스트를 비교합니다. 실제 환경에서는 더 나은 유사도 매칭을 위해 더욱 정교한 NLP 기법을 구현하는 것을 고려해 보세요.
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.
