GitHub MCP Wrapper

GitHub data through Model Context Protocol. Let AI agents query repositories, issues, PRs, and contributors via standardized protocol.

GitHub is a goldmine of technical intelligence. This actor exposes GitHub data through the Model Context Protocol (MCP), allowing any MCP-compatible AI agent to query repositories, analyze issues, track contributors, and inspect pull requests programmatically. Train AI agents on your codebase or competitors'.

⚡ What You Get

GitHub Repository Intelligence Report
├── Repository: anthropic/anthropic-sdk-python
├── Basic Metrics
│   ├── Stars: 8,247
│   ├── Forks: 892
│   ├── Watchers: 234
│   ├── Open Issues: 47
│   ├── Open PRs: 12
│   └── Last Updated: 2 hours ago
├── Repository Intelligence 👈 Understand active projects at a glance
│   ├── Language: Python
│   ├── License: MIT
│   ├── Created: 2023-03-15
│   ├── Main Contributors: 23
│   ├── Commit Frequency: 8-12 per day
│   └── Activity Trend: Very Active
├── Code Metrics
│   ├── Total Commits: 4,287
│   ├── Total Files: 892
│   ├── Total Lines of Code: 127,000
│   ├── Test Coverage: 89%
│   └── Documentation Quality: Excellent
├── Active Contributors
│   ├── dario-amodei (commits: 847, PRs: 34)
│   ├── tom-brown (commits: 621, PRs: 28)
│   ├── jane-smith (commits: 456, PRs: 19)
│   ├── Total Contributors: 23
│   └── New Contributors (30d): 4
├── Issue Analysis
│   ├── Total Issues (all time): 2,341
│   ├── Open Issues: 47
│   ├── Avg Resolution Time: 3.2 days
│   ├── High Priority (open): 8
│   ├── Top Issue Themes:
│   │   ├── "Documentation requests": 12
│   │   ├── "Performance improvements": 8
│   │   ├── "API consistency": 6
│   │   └── "Bug reports": 4
│   └── Label Usage: Well organized
├── Pull Request Pipeline
│   ├── Open PRs: 12
│   ├── Avg Time to Merge: 2.1 days
│   ├── Avg Review Time: 4 hours
│   └── Authors of Open PRs: 7 external, 5 internal
└── MCP Integration Status
    ├── Protocol: Active ✓
    ├── Query Capabilities: Full
    ├── Real-time Updates: Enabled
    ├── AI Agent Access: Ready
    └── Typical Use: "Summarize this repo's architecture"

🎯 Use Cases

• AI Code Analysis: Let Claude, ChatGPT, or your own agents analyze open-source projects. "What's the architecture of this repo?"
• Competitive Research: Query competitor repos (if public). Understand their tech choices, contributor base, roadmap from issues.
• Due Diligence: Analyzing acquisition target? Check their GitHub. Code quality, commit frequency, issue backlog tell the real story.
• Developer Intelligence: Track which developers are contributing to what. Build talent networks.
• Dependency Analysis: Understand projects you depend on. Check contributor activity, issue resolution time, maintenance quality.
• Open Source Contributions: Find projects matching your expertise. See contribution patterns, maintainer responsiveness.

📊 Sample Output

{
  "repository": {
    "name": "anthropic-sdk-python",
    "owner": "anthropic",
    "url": "https://github.com/anthropic/anthropic-sdk-python",
    "description": "Python SDK for Anthropic APIs",
    "language": "Python",
    "license": "MIT"
  },
  "metrics": {
    "stars": 8247,
    "forks": 892,
    "watchers": 234,
    "open_issues": 47,
    "open_pull_requests": 12,
    "total_commits": 4287,
    "total_contributors": 23,
    "last_updated": "2024-02-15T10:30:00Z"
  },
  "activity": {
    "commits_per_day": 10.2,
    "activity_trend": "very_active",
    "new_contributors_30d": 4,
    "commit_frequency": "8-12 per day"
  },
  "code_quality": {
    "test_coverage_percent": 89,
    "documentation_quality": "excellent",
    "lines_of_code": 127000,
    "total_files": 892
  },
  "top_contributors": [
    {
      "username": "dario-amodei",
      "contributions": 847,
      "pull_requests": 34,
      "join_date": "2023-03-15"
    },
    {
      "username": "tom-brown",
      "contributions": 621,
      "pull_requests": 28
    }
  ],
  "issues": {
    "total_all_time": 2341,
    "open": 47,
    "avg_resolution_days": 3.2,
    "high_priority_open": 8,
    "top_issue_types": [
      {"type": "Documentation requests", "count": 12},
      {"type": "Performance improvements", "count": 8}
    ]
  },
  "pull_requests": {
    "open": 12,
    "avg_time_to_merge_days": 2.1,
    "avg_review_time_hours": 4,
    "external_authors": 7,
    "internal_authors": 5
  },
  "mcp_integration": {
    "protocol_status": "active",
    "query_capabilities": "full",
    "real_time_updates": true,
    "ai_agent_ready": true
  }
}

Field Descriptions:

• top_contributors: Active developers, their contribution history
• avg_resolution_days: How quickly issues get closed (maintenance quality)
• avg_time_to_merge_days: How fast the team merges PRs (project velocity)
• test_coverage_percent: Code quality indicator
• activity_trend: "very_active" = healthy project; "stale" = abandoned

🔗 Integrations & Automation

MCP Client Integration: Direct AI agent access via protocol. Query repos in conversation.

Webhook to Slack: New major release? New contributor? Slack alert.

Email Digests: Weekly summary of repo activity, top contributors, new issues.

REST API: Build dashboards showing repo health across your ecosystem.

Custom Workflows: Combine GitHub data with other sources (Crunchbase funding, tech stack, reviews).

See integration docs →

🔌 Works Great With

• Crunchbase Company Scraper — Company raised Series B? Query their repos to understand their engineering depth.
• Website Tech Stack Detector — Detect what framework a company uses, then find their GitHub repos.
• Job Board Aggregator — Analyze job postings, then check company's GitHub for recent tech choices.
• Competitive Intelligence Engine — GitHub data is core to competitive analysis.

💰 Cost & Performance

Typical run: Query repository data, analyze 100 commits, profile 20 contributors in 2 minutes for ~$1.25.

That's $0.0125 per analysis — cheaper than 30 seconds of manual exploration.

Compare to manual: One developer manually exploring a GitHub repo: 30+ minutes. At $50/hour, that's $25. We do it in 2 minutes for $1.25.

🛡️ Built Right

• Official GitHub API via authenticated requests (higher rate limits)
• Real-time data no caching delays
• Contributor analysis identifies core team and activity patterns
• Issue parsing extracts themes, priorities, resolution time
• MCP protocol compliance works with any MCP-compatible client
• Error handling gracefully handles private repos, deleted repos

Fresh data. Zero guesswork. Be the first to know.

📧 Email alerts · 🔗 Webhook triggers · 🤖 MCP compatible · 📡 API access

Built by Creator Fusion — OSINT tools that actually work.