convez.ai
MCP ServerBusca & PesquisaIntermediário
carolinacherry

GitHub Talent MCP

carolinacherry/github-talent-mcp

Busca e rank de talentos técnicos do GitHub via IA

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que busca, pontua e classifica desenvolvedores do GitHub para recrutamento técnico. Integra-se ao Claude para analisar perfis, calcular scores de atividade e relevância, e ranquear candidatos baseado em critérios customizáveis como linguagens principais, contribuições recentes e presença em projetos open source.

Instalação

$npx convez-ai carolinacherry/github-talent-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
9
Forks
1
Acompanhando
0
Saúde
42%
Último commit
há 3 semanas
Versão
—
Issues abertas
2
Contribuidores
1

Casos de uso

  • Encontrar e avaliar candidatos para posições técnicas específicas
  • Ranquear contribuidores de repositórios por relevância e atividade
  • Análise automática de perfis GitHub com scoring multidimensional

Veredito

Ferramenta sólida e bem-estruturada para automação de recrutamento técnico. Executa buscas diretas na API do GitHub, calcula scores transparentes (atividade + relevância) e fornece rankings acionáveis — ideal para times de RH/tech que precisam de triagem objetiva de candidatos.

README

A tradução para o português deste README ainda está na fila.

github-talent-mcp

License: MIT Python 3.14+ MCP Claude GitHub API

MCP server that searches, scores, and ranks GitHub developers for technical recruiting.

Demo

https://github.com/user-attachments/assets/2dfd82b4-3eb5-4f2b-bc0a-2580b95043e4

Profile deep dive

Get the full developer profile and activity score for torvalds on GitHub

Claude calls get_developer_profile("torvalds") and returns:

FieldValue
Activity Score150 (reputation floor applied)
LocationPortland, OR
Followers293,321
Stars Received235,068
Primary LanguageC (98.1%)
Commits (90d)0
PRs (90d)0
Notable Reposlinux (183K stars), libdc-for-dirk, subsurface-for-dirk, uemacs, pesern-resolve
Profile READMENo
HireableNo

Torvalds has zero recent GitHub activity because kernel development flows through mailing lists, not GitHub PRs. The reputation floor (293K followers) overrides the behavioral score and sets it to 150.

Repo contributor ranking

Get the top contributors to huggingface/transformers and rank them for a founding ML engineer role at an AI startup

Claude calls get_repo_contributors("huggingface/transformers") → rank_candidates on the top 24 contributors:

RankDeveloperCombined ScoreActivityRelevanceStrengths
1stas0083.4150724,553 stars, contributes to major OSS, MIT-licensed repos
2cyyever80.8120641,217 followers, active contributor, profile README
3Cyrilvallez77.212056Active: 13 commits + 57 PRs in 90 days, strong OSS presence
4ArthurZucker74.41204837 PRs in 90 days, contributes to huggingface/transformers
5ydshieh72.012040Active: 9 commits + 40 PRs in 90 days

Combined score = activity × 0.4 + relevance × 0.6. Relevance is keyword overlap with the job description (ML, AI, startup, engineer, etc.).

Installation

1. Clone and install

git clone https://github.com/carolinacherry/github-talent-mcp.git
cd github-talent-mcp
python3 -m venv .venv && source .venv/bin/activate
pip install -e .

2. Create a GitHub personal access token

Go to github.com/settings/tokens and create a fine-grained or classic token with these scopes:

ScopeWhy
read:userRead user profiles and search users
public_repoRead public repo data, languages, contributors

Create a .env file in the project root:

GITHUB_TOKEN=ghp_xxxxxxxxxxxx

3. Connect to Claude

Claude Code (CLI)

One command:

claude mcp add github-talent -- /path/to/github-talent-mcp/.venv/bin/python3 -m github_talent_mcp

Then set the token as an environment variable. Either:

  • Export it in your shell: export GITHUB_TOKEN=ghp_xxxxxxxxxxxx
  • Or keep it in the .env file — the server reads it via python-dotenv on startup

Restart Claude Code to pick up the new server. Verify with /mcp — you should see 8 tools under github-talent.

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "github-talent": {
      "command": "/path/to/github-talent-mcp/.venv/bin/python3",
      "args": ["-m", "github_talent_mcp"],
      "cwd": "/path/to/github-talent-mcp",
      "env": {
        "GITHUB_TOKEN": "ghp_xxxxxxxxxxxx"
      }
    }
  }
}

Restart Claude Desktop. The tools will appear in the toolbox icon.

Try It

Once installed, paste these prompts to verify everything works:

Basic search:

Find Python developers in Raleigh active in the last 60 days

Profile deep dive:

Get the full developer profile and activity score for torvalds on GitHub

Full workflow:

Find 10 ML engineers in San Francisco active in the last 30 days, then rank them for a senior LLM inference engineer role

Repo contributors:

Get the top contributors to huggingface/transformers and rank them for a founding ML engineer role at an AI startup

JD scoring:

Score these candidates against this job description: [paste JD]. Candidates: tiangolo, karpathy, hwchase17

Compare candidates:

Compare tiangolo and hwchase17 for a Senior Python AI Engineer role

Bulk scoring:

Score these 10 GitHub usernames and give me a ranked table: [paste list]

Outreach:

Generate a casual recruiter message for tiangolo about a Senior Python role at Acme. My name is Daniel.

Tools

ToolDescription
search_developersSearch GitHub users by language, location, activity, followers. For topic-based sourcing, use get_repo_contributors on relevant repos instead.
get_developer_profileDeep profile enrichment: languages, stars, commits + PRs, OSS contributions, license breakdown, profile README, and activity score with breakdown.
rank_candidatesRank usernames against a job description. Returns sorted candidates with combined score, strengths, gaps, and reasoning.
score_against_jdScore candidates against a JD with per-dimension breakdown (tech stack, experience level, OSS signal, leadership). Returns gaps and personalized interview questions.
compare_candidatesSide-by-side comparison of 2-5 candidates. Shows dimension winners and a recommendation. Optionally scored against a JD.
bulk_scoreScore up to 100 GitHub usernames in one call. Returns a ranked markdown table or CSV. Supports optional JD matching.
generate_outreachGenerate personalized recruiter messages (short/medium/detailed) that reference the candidate's actual repos and contributions. Requires your company name and sender name. Casual or formal tone.
get_repo_contributorsTop contributors for any repo. Accepts owner/repo or full URL. The fastest way to source for a specific domain.

Scoring

The activity score combines two layers: behavioral signals (what you did recently) and a reputation floor (what you've built over time).

Behavioral Score (0-205)

SignalMax PointsHow
Commits + PRs (last 90 days)60Push commits + PR opens (PRs weighted x3). Captures both push-based and PR-based workflows.
Stars on repos40Personal repo stars + stars on repos you contribute to. Org repo maintainers get credit.
Profile README20Presence of a profile README (github.com/username/username).
Followers20Capped at 20.
Repos with descriptions20Ratio of repos that have descriptions. Signal of care and polish.
Permissive license repos15Has at least one repo with MIT, Apache-2.0, BSD, ISC, or Unlicense.
Major OSS contributions30PRs, pushes, or issues on repos you don't own. Capped at 3 repos (10 pts each).

Reputation Floor

The behavioral score alone penalizes developers whose work doesn't produce GitHub events — Torvalds works through mailing lists, senior maintainers merge via org bots, and many engineers work in private repos.

The reputation floor ensures cumulative impact isn't erased by a quiet quarter:

ThresholdFloor
10K+ followers or 50K+ stars150
1K+ followers or 5K+ stars120
500+ followers or 1K+ stars100
100+ followers or 200+ stars80

The final score is max(behavioral_score, reputation_floor). If the floor is applied, the breakdown includes a reputation_floor field so you know.

Score Tiers

  • 150+ — exceptional (top OSS maintainers, well-known engineers)
  • 120-149 — strong signal, worth reaching out
  • 80-119 — solid developer with meaningful public work
  • 40-79 — active but limited public signal
  • <40 — low signal (likely private work or junior)

Ranking

rank_candidates combines the activity score with a relevance score (0-100) based on keyword overlap between the job description and the candidate's profile (bio, languages, repo topics, README). The combined score weights relevance at 60% and activity at 40% — a high-activity developer with no overlap to the job shouldn't outrank a relevant one.

Rate Limits

GitHub REST API: 5,000 requests/hour with token. A typical workflow (search + enrich 5 candidates + rank) uses ~60-100 API calls. Profile results are cached within a session to avoid redundant calls during ranking.

License

MIT

Ver o original no GitHub

Bom para

Relacionados