# GitHub AI Agent & MCP Repo Tracker (`agentdataco/github-ai-agent-tracker`) Actor

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.

- **URL**: https://apify.com/agentdataco/github-ai-agent-tracker.md
- **Developed by:** [Agent Data Co](https://apify.com/agentdataco) (community)
- **Categories:** AI, Developer tools
- **Stats:** 2 total users, 1 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per event

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## 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:

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

### Output

Each dataset item looks like this:

```json
{
  "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](https://agentdataco.com) 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](https://agentdataco.com/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

# Actor input Schema

## `topics` (type: `array`):

Repo topics to track (one search per topic, results merged & de-duplicated).

## `keywords` (type: `array`):

Optional extra keywords searched in repo name and description.

## `query` (type: `string`):

Optional extra raw GitHub search query.

## `language` (type: `string`):

Optional language filter, e.g. Python, TypeScript.

## `perQueryLimit` (type: `integer`):

Max repos fetched per topic/keyword before merging.

## `sort` (type: `string`):

Sort.

## `createdAfter` (type: `string`):

Optional. Limits to repos created after this date. Empty = no filter.

## `minStars` (type: `integer`):

Minimum stars.

## `maxItems` (type: `integer`):

Max results.

## `githubToken` (type: `string`):

Raises rate limit from 10 to 30 requests/min (search) / 5k/h (authenticated). Store as a secret input.

## `allowEmpty` (type: `boolean`):

Allow empty results (tests).

## Actor input object example

```json
{
  "topics": [
    "mcp-server",
    "mcp",
    "model-context-protocol",
    "ai-agent",
    "ai-agents",
    "llm-agent",
    "agentic-ai",
    "autonomous-agents"
  ],
  "keywords": [],
  "perQueryLimit": 100,
  "sort": "stars",
  "minStars": 0,
  "maxItems": 50,
  "allowEmpty": false
}
```

# Actor output Schema

## `results` (type: `string`):

Dataset items produced by this run (one item per charged result).

## `runSummary` (type: `string`):

Count of results, duration and whether the charge limit was hit.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("agentdataco/github-ai-agent-tracker").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("agentdataco/github-ai-agent-tracker").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call agentdataco/github-ai-agent-tracker --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,agentdataco/github-ai-agent-tracker"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/0O0xxQrJYdDbkmILk/builds/iCm8HPhsfpf14D4dT/openapi.json