# API Documentation Crawler for RAG & AI Agents (`ahampton83/api-docs-rag-crawler`) Actor Crawl API documentation sites and extract structured, LLM-ready content. Use via Apify Console/API or connect as an MCP server for Claude, Cursor, and other AI agents. - **URL**: https://apify.com/ahampton83/api-docs-rag-crawler.md - **Developed by:** [Aaron Hampton](https://apify.com/ahampton83) (community) - **Categories:** AI, Developer tools, MCP servers - **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing from $5.00 / 1,000 page crawleds 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/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. 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. Actors are written with capital "A". ## 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. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## API Documentation Crawler for RAG & AI Agents Crawl API documentation sites and extract clean, structured content for AI models, RAG pipelines, and vector databases. Use it as a normal Apify Actor or connect it to Claude, Cursor, and other MCP-compatible clients. ### What it does This Actor crawls API documentation websites and returns structured records for each page: - **Title & description** - **Heading hierarchy** (with anchor IDs) - **Markdown-formatted content** - **Plain text** (for simple embedding) - **Detected API endpoints** (method + path, when visible on the page) - **Code examples** - **Outbound links** - **Metadata** (canonical URL, OpenGraph tags) You can also switch to **chunking mode** to get pre-split text snippets ready for vector DB ingestion. ### Why use this? - **Feed RAG pipelines** with clean, structured API docs. - **Power AI agents** that need to answer questions about an API. - **Avoid brittle copy-paste** from docs into LLM context windows. - **MCP-native:** call it as a tool from Claude, Cursor, ChatGPT, and other MCP clients. ### How to use #### Apify Console / API Provide one or more start URLs and optional limits: ```json { "startUrls": ["https://docs.apify.com/api/v2"], "maxPages": 20, "maxDepth": 2, "outputFormat": "full" } ```` #### MCP mode Connect the Actor as an MCP server in Cursor/Claude Desktop: ```json { "mcpServers": { "api-docs-crawler": { "url": "https://AHampton83--api-docs-rag-crawler.apify.actor/mcp" } } } ``` Available tools: - `crawl_api_docs(startUrl, maxPages?, maxDepth?)` — crawl docs and return structured page summaries. - `get_page_chunks(startUrl, maxPages?, chunkSize?, chunkOverlap?)` — return pre-chunked text for vector DBs. ### Output schema #### Full format (`outputFormat: "full"`) ```json { "url": "https://docs.example.com/api/v1/users", "title": "Users API", "description": "Manage users via the REST API", "headings": [{ "level": 1, "text": "Users API", "id": "users-api" }], "markdown": "# Users API\n\n## Get all users\n\n`GET /api/v1/users`", "text": "Users API Get all users GET /api/v1/users ...", "endpoints": [{ "method": "GET", "path": "/api/v1/users", "confidence": "high" }], "codeBlocks": [{ "language": "bash", "content": "curl /api/v1/users" }], "links": ["https://docs.example.com/api/v1/orders"], "metadata": { "canonicalUrl": "...", "ogTitle": "...", "ogDescription": "..." }, "crawledAt": "2026-07-04T00:00:00.000Z" } ``` #### Chunks format (`outputFormat: "chunks"`) ```json { "chunkIndex": 0, "url": "https://docs.example.com/api/v1/users", "title": "Users API", "text": "...", "headings": [{ "level": 2, "text": "Get all users" }], "tokenEstimate": 250 } ``` ### Pricing This Actor uses **Pay Per Event (PPE)** billing: | Event | Price | Notes | |---|---|---| | `apify-actor-start` | $0.00005 | Platform-provided synthetic start event | | `page-crawled` | $0.005 | First 10 pages per run/tool-call are free | | `chunk-generated` | $0.001 | First 10 chunks per run/tool-call are free | | `tool-call` | $0.01 | Per MCP tool call | Volume discounts apply based on the user's Apify plan tier. ### Publish & monetize To activate monetization and publish this Actor on Apify Store: 1. Open the Actor in Apify Console: https://console.apify.com/actors/Dtlhc1snKkwxoikZh 2. Go to the **Publication** tab and click **Set up monetization**. 3. In the pricing step, keep `apify-actor-start` and add these custom events with the exact slugs used in the code: - `page-crawled` — $0.005 - `chunk-generated` — $0.001 - `tool-call` — $0.01 4. **Do not enable `apify-default-dataset-item`**: the Actor already charges manually per page/chunk, so the synthetic dataset-item event would double-charge users. 5. Complete the **Primary event** and **Review** steps, then submit for Store approval. Payouts require a verified developer account with tax and payment details in Apify Console. ### Limits - `maxPages`: up to 500 per normal run, 100 per MCP tool call. - Crawls only same-origin links by default (configurable via `includeUrlGlobs`). - Static HTML only — Cheerio crawler does not execute JavaScript. ### Use cases - Build a custom API assistant for your product. - Keep vector store embeddings in sync with live docs. - Generate SDK examples from existing documentation. - Competitive analysis of public APIs. ### Support Open an issue or reach out via the Apify Store page. # Actor input Schema ## `startUrls` (type: `array`): One or more API documentation URLs where crawling should begin. ## `maxPages` (type: `integer`): Maximum number of pages to crawl per run. ## `maxDepth` (type: `integer`): Maximum link depth to follow from start URLs. ## `outputFormat` (type: `string`): Return full page records or pre-chunked text for vector DBs. ## `chunkSize` (type: `integer`): Approximate words per chunk when outputFormat is 'chunks'. ## `chunkOverlap` (type: `integer`): Words of overlap between chunks. ## `includeUrlGlobs` (type: `array`): Only crawl URLs matching these glob patterns (e.g. **/api/**). Leave empty to crawl all same-origin links. ## `excludeUrlGlobs` (type: `array`): Skip URLs matching these glob patterns (e.g. **/blog/**, **/changelog/**). ## Actor input object example ```json { "startUrls": [ { "url": "https://docs.apify.com/api/v2" } ], "maxPages": 50, "maxDepth": 3, "outputFormat": "full", "chunkSize": 1000, "chunkOverlap": 100, "includeUrlGlobs": [], "excludeUrlGlobs": [] } ``` # 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 '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "startUrls": [ { "url": "https://docs.apify.com/api/v2" } ], "includeUrlGlobs": [], "excludeUrlGlobs": [] }; // Run the Actor and wait for it to finish const run = await client.actor("ahampton83/api-docs-rag-crawler").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 '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "startUrls": [{ "url": "https://docs.apify.com/api/v2" }], "includeUrlGlobs": [], "excludeUrlGlobs": [], } # Run the Actor and wait for it to finish run = client.actor("ahampton83/api-docs-rag-crawler").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "startUrls": [ { "url": "https://docs.apify.com/api/v2" } ], "includeUrlGlobs": [], "excludeUrlGlobs": [] }' | apify call ahampton83/api-docs-rag-crawler --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=ahampton83/api-docs-rag-crawler", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "API Documentation Crawler for RAG & AI Agents", "description": "Crawl API documentation sites and extract structured, LLM-ready content. Use via Apify Console/API or connect as an MCP server for Claude, Cursor, and other AI agents.", "version": "0.1", "x-build-id": "1SC5VDUgJOCHcgSJO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ahampton83~api-docs-rag-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ahampton83-api-docs-rag-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ahampton83~api-docs-rag-crawler/runs": { "post": { "operationId": "runs-sync-ahampton83-api-docs-rag-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ahampton83~api-docs-rag-crawler/run-sync": { "post": { "operationId": "run-sync-ahampton83-api-docs-rag-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "One or more API documentation URLs where crawling should begin.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of pages to crawl per run.", "default": 50 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum link depth to follow from start URLs.", "default": 3 }, "outputFormat": { "title": "Output format", "enum": [ "full", "chunks" ], "type": "string", "description": "Return full page records or pre-chunked text for vector DBs.", "default": "full" }, "chunkSize": { "title": "Chunk size (words)", "minimum": 50, "maximum": 3000, "type": "integer", "description": "Approximate words per chunk when outputFormat is 'chunks'.", "default": 1000 }, "chunkOverlap": { "title": "Chunk overlap (words)", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Words of overlap between chunks.", "default": 100 }, "includeUrlGlobs": { "title": "Include URL patterns", "type": "array", "description": "Only crawl URLs matching these glob patterns (e.g. **/api/**). Leave empty to crawl all same-origin links.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "excludeUrlGlobs": { "title": "Exclude URL patterns", "type": "array", "description": "Skip URLs matching these glob patterns (e.g. **/blog/**, **/changelog/**).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```