GitHub AI Agent & MCP Repo Tracker — Trending Repositories

Find newly created and trending GitHub repos for AI agents, MCP servers, LLM agents and agentic frameworks. Fresh data via the official GitHub Search API.

What does GitHub AI Agent Tracker do?

This Actor queries the official GitHub Search API for repositories matching AI-agent and Model Context Protocol (MCP) topics, returns structured JSON (stars, forks, language, license, topics, last push) and can be scheduled daily to catch new launches. Provide an optional GitHub personal access token for higher rate limits.

Why use it?

• Uses only the official GitHub REST Search API — no scraping, no ToS conflict
• Defaults cover MCP servers, AI agents, LLM agents and agentic frameworks
• Optional token input for authenticated rate limits
• Fail-loudly empty-result guard — never pays for empty "success"
• Ready for Make / Zapier / n8n / Apify MCP

Data source

GitHub REST API GET /search/repositories (https://docs.github.com/en/rest/search). Public repository metadata only.

Input

• topics: GitHub topics to track (merged, de-duplicated)
• keywords: Extra name/description keywords
• createdAfter: YYYY-MM-DD filter
• minStars: Minimum stars
• language: Language filter
• sort: stars | updated | created
• maxItems: Cap on results
• githubToken: Optional secret PAT (higher rate limit)

Example input:

{
  "topics": [
    "mcp-server",
    "ai-agent"
  ],
  "createdAfter": "2026-09-01",
  "minStars": 20,
  "maxItems": 50
}

Output

Each dataset item looks like this:

{
  "full_name": "modelcontextprotocol/servers",
  "html_url": "https://github.com/modelcontextprotocol/servers",
  "stargazers_count": 50000,
  "language": "TypeScript",
  "topics": [
    "mcp",
    "ai"
  ],
  "created_at": "2024-11-19T00:00:00Z"
}

Export as JSON, CSV, Excel or HTML, or pull via the Apify API, webhooks, Make, Zapier, n8n or the Apify MCP server.

How much does it cost?

Pay per event: $0.001 per run + $0.002 per result (≈ $2.00 per 1,000 results). You are never charged for results on a failed run: if no data is found, the run fails loudly with an explanation instead of returning an empty "success".

Use cases

• AI agent researchers tracking new MCP servers
• Investors / analysts monitoring agentic open-source activity
• Directories that need a daily feed of new AI agent repos
• Competitive intel on agent frameworks

Scheduling & monitoring

Schedule it daily or weekly in Apify Console and connect a webhook/Slack/email integration to get new items automatically.

FAQ

Is this legal? It uses the official GitHub REST API under GitHub's API Terms. Only public repository metadata is returned.. No personal data is collected.

Something broke? Open an issue on the Issues tab; the actor is tested daily.

---

Built and maintained by Agent Data Co — reliable AI-ecosystem data for agents and analysts.

Need history and trends? Use the Agent Data Co API

This Actor gives you a fresh snapshot each run. Agent Data Co runs the same collection every day and keeps an append-only archive, so you can get daily history per entity, 1d/7d/30d top movers and change events without scheduling runs or storing results yourself:

• REST: GET https://agentdataco.com/api/v1/github-ai-repos and /api/v1/github-ai-repos/history?entity=... (docs)
• MCP for AI agents: https://agentdataco.com/mcp (Streamable HTTP; free sample tools work without a key)
• Free sample, no key: https://agentdataco.com/api/v1/sample?name=github-ai-repos
• Public trend pages: https://agentdataco.com/trends · example: https://agentdataco.com/repo/affaan-m/ECC
• Plans: Starter $19/mo (latest data + 30-day history), Pro $49/mo (full archive, trends, priority watchlist): https://agentdataco.com/#pricing