Irmu in Replit

We have not confirmed the exact Replit menu for custom MCP servers. If you don't see the option, use the API steps below — they work in every Repl.

1. 1

   Add a custom MCP server

   If Replit Agent offers custom MCP servers in your workspace, add one with the Irmu URL.

   text

   Copy

   https://app.irmu.com/mcp

2. 2

   Authenticate

   Sign in with OAuth, or if the form asks for headers, add an Authorization header with your API key:

   json

   Copy

   {
     "mcpServers": {
       "irmu": {
         "url": "https://app.irmu.com/mcp",
         "headers": {
           "Authorization": "Bearer YOUR_IRMU_API_KEY"
         }
       }
     }
   }

All MCP tools and other clients →

1. 1

   Add the secret

   Open Tools → Secrets in your Repl and add IRMU_API_KEY with a key from the Irmu dashboard.

2. 2

   Python

   Install requests and call Irmu:

   python

   Copy

   import os, time, requests
   
   API = "https://app.irmu.com/api"
   HEADERS = {"Authorization": f"Bearer {os.environ['IRMU_API_KEY']}"}
   
   def scrape(url: str) -> dict:
       res = requests.get(f"{API}/crawl", params={"url": url, "format": "markdown"}, headers=HEADERS)
       # Slow pages return 202 with a job id: poll until ready (polling is free).
       while res.status_code == 202:
           job = res.json()["job_id"]
           time.sleep(3)
           res = requests.get(f"{API}/crawl/{job}", headers=HEADERS)
       res.raise_for_status()
       return res.json()

3. 3

   Node

   Or in Node 18+, with no extra packages:

   typescript

   Copy

   // Server-side only. Reads IRMU_API_KEY from the environment.
   export async function scrape(url: string) {
     const key = process.env.IRMU_API_KEY;
     const params = new URLSearchParams({ url, format: "markdown" });
     let res = await fetch(`https://app.irmu.com/api/crawl?${params}`, {
       headers: { Authorization: `Bearer ${key}` },
     });
     // Slow pages return 202 with a job id: poll until ready (polling is free).
     while (res.status === 202) {
       const { job_id } = await res.json();
       await new Promise((r) => setTimeout(r, 3000));
       res = await fetch(`https://app.irmu.com/api/crawl/${job_id}`, {
         headers: { Authorization: `Bearer ${key}` },
       });
     }
     if (!res.ok) throw new Error(`Irmu error ${res.status}`);
     return res.json();
   }

• "Write a Flask app that takes a URL, scrapes it with Irmu using IRMU_API_KEY, and returns the page as markdown."

  Uses:crawl

• "Build a script that asks ChatGPT 'best CRM for startups' from the US through Irmu every week and logs which brands are named."

  Uses:chatgpt

• "Create a bot that screenshots our homepage from Germany every morning with Irmu."

  Uses:screenshot

Need clicks, typing or pagination? See the recipe blocks reference.

What does it cost?

The same credits as the REST API: 1 credit for a plain page, more with JavaScript rendering or premium IPs, 30 flat for Google AI Overview, ChatGPT and Booking.com. Using MCP adds nothing. See /pricing.

I get a 401 error.

The API key is missing or wrong. Check the secret is named IRMU_API_KEY, has no extra spaces, and is read on the server, not in browser code.

I get a 202 instead of data.

The page took longer than the request window. The response carries a job id; call GET /crawl/{job} until it stops returning 202. Collecting is free.

Should I use MCP or the API?

MCP lets the AI agent fetch pages while it builds or answers you. The API is for the app you publish, so your users' actions trigger scrapes. Most projects use both.