# Docs /llms.txt & GitHub Changelog Gleaner MCP (`shikitoka/docs-changelog-mcp`) Actor

Zero-browser, sub-second documentation and changelog gleaner for AI agents (MCP) and RAG pipelines. Routes /llms.txt -> raw .md -> GitHub Releases/Atom -> Readability HTML-to-Markdown without Chromium cold-start penalties.

- **URL**: https://apify.com/shikitoka/docs-changelog-mcp.md
- **Developed by:** [Nanda Leo Ardana](https://apify.com/shikitoka) (community)
- **Features:** Limited permissions, Single-tenant, Server interface
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $4.00 / 1,000 docs gleaneds

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

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

## Docs `/llms.txt` & GitHub Changelog Gleaner (`docs-changelog-mcp`)

Zero-browser, sub-second documentation and release-notes gleaner for **AI coding agents (MCP)**, **RAG pipelines**, and **n8n / Make** workflows.

Eliminates full-Chromium cold-start penalties by smart-routing `/llms.txt` → raw `.md` → content-negotiated Markdown → `Readability` HTML-to-Markdown, and GitHub Releases API → `releases.atom` → `CHANGELOG.md`.

### What It Does

1. **Smart Docs Gleaning (`glean_docs`)**:
   - Probes `/llms.txt` and `/llms-full.txt` first; when a `query` is provided, ranks matching index entries and fetches the top `maxPages` pages in parallel.
   - Probes `Accept: text/markdown` and `.md` URL suffixes (supported by Mintlify, Docusaurus, GitBook, Nextra, Cloudflare Docs).
   - Falls back to pure-JS `linkedom` + `@mozilla/readability` + `turndown` HTML-to-Markdown (zero Chromium).
   - Enforces a configurable `maxChars` token budget so LLM context windows stay clean.
2. **Release Notes & Changelog Gleaning (`get_changelog`)**:
   - Accepts any GitHub `owner/repo` slug, GitHub URL, or Atom/RSS/`CHANGELOG.md` URL.
   - Automatically falls back to `github.com/{owner}/{repo}/releases.atom` (no API rate limit) and raw `CHANGELOG.md`.
   - Flags `BREAKING` changes, filters prereleases or `sinceVersion`, and budgets Markdown output.

### MCP Tools (Standby Mode — `/mcp`)

- **`glean_docs`**: `{ url, query?, maxPages?, maxChars?, preferLlmsTxt? }`
- **`get_changelog`**: `{ repo, limit?, sinceVersion?, includePrereleases?, maxChars? }`

### Batch Input Example

```json
{
  "urls": ["https://docs.apify.com/llms.txt"],
  "query": "standby mcp",
  "repos": ["apify/crawlee"],
  "limit": 3,
  "maxChars": 8000
}
```

### Pricing (Pay-Per-Event)

- **`docs-gleaned`** (`$0.004` / URL): Charged **only** after clean Markdown is extracted. Failed/blocked fetches are **never charged**.
- **`changelog-fetched`** (`$0.003` / repo or feed): Charged **only** after release notes are retrieved.

### Connect via MCP (Claude, Cursor, Windsurf)

```json
{
  "mcpServers": {
    "docs-changelog-mcp": {
      "type": "http",
      "url": "https://shikitoka--docs-changelog-mcp.apify.actor/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_APIFY_TOKEN"
      }
    }
  }
}
```

Or via Apify's hosted MCP router: `https://mcp.apify.com/?tools=shikitoka/docs-changelog-mcp`.

### n8n / Make HTTP Integration

```bash
POST https://api.apify.com/v2/acts/shikitoka~docs-changelog-mcp/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN
Content-Type: application/json

{
  "urls": ["https://docs.apify.com/llms.txt"],
  "query": "pay per event",
  "repos": ["apify/crawlee"],
  "limit": 3
}
```

# Actor input Schema

## `urls` (type: `array`):

Documentation site or page URLs to glean (auto-probes /llms.txt, .md suffix, and Readability HTML->Markdown).

## `url` (type: `string`):

Optional single documentation URL for quick runs.

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

Optional keyword query to rank and fetch the most relevant pages from an /llms.txt index (e.g. 'pay per event' or 'standby mcp').

## `repos` (type: `array`):

GitHub 'owner/repo' slugs, GitHub repo URLs, or Atom/RSS/CHANGELOG.md URLs to fetch structured release notes.

## `repo` (type: `string`):

Optional single GitHub 'owner/repo' or changelog URL.

## `limit` (type: `integer`):

Maximum number of recent releases to return per repository (1-20).

## `maxPages` (type: `integer`):

When gleaning an /llms.txt index with a query, maximum matching doc pages to fetch (0-5).

## `maxChars` (type: `integer`):

Token-budget cap for returned Markdown content per item (500-50000).

## `includePrereleases` (type: `boolean`):

Include alpha/beta/rc prereleases in changelog results.

## Actor input object example

```json
{
  "urls": [
    "https://docs.apify.com/llms.txt"
  ],
  "repos": [
    "apify/crawlee"
  ],
  "limit": 5,
  "maxPages": 3,
  "maxChars": 8000,
  "includePrereleases": false
}
```

# Actor output Schema

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

No description

# 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 = {
    "urls": [
        "https://docs.apify.com/llms.txt"
    ],
    "repos": [
        "apify/crawlee"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("shikitoka/docs-changelog-mcp").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 = {
    "urls": ["https://docs.apify.com/llms.txt"],
    "repos": ["apify/crawlee"],
}

# Run the Actor and wait for it to finish
run = client.actor("shikitoka/docs-changelog-mcp").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 '{
  "urls": [
    "https://docs.apify.com/llms.txt"
  ],
  "repos": [
    "apify/crawlee"
  ]
}' |
apify call shikitoka/docs-changelog-mcp --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,shikitoka/docs-changelog-mcp"
        }
    }
}
```

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/xnnsEVjVTKsuwABzv/builds/bmB7KylvdLAXUldsz/openapi.json
