# Firecrawl MCP connector

The Firecrawl connector lets Claude, ChatGPT, Cursor, and the Elaichi Agent scrape a page, crawl a whole site, map its links, or extract structured data from the web, with every request running under your Firecrawl account and recorded in an audit log.

Source: https://elaichi.ai/connectors/firecrawl/

## Facts

| | |
| --- | --- |
| Application | Firecrawl |
| Category | Application Development |
| AI tools | 30 |
| Authentication | Connects with an API key |
| Needs your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent |
| Tools advertised by name | Yes |

## What you can ask once Firecrawl is connected

- Which Firecrawl crawls returned errors this week?
- List batch scrapes created by the Docs team.
- Show browsers still running longer than an hour.

## Connect Firecrawl in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Firecrawl.
2. Optionally set Share with, then press Connect.
3. Paste a Firecrawl API key. One person generates a token in Firecrawl and pastes it once. Everyone else works through Share with, and never sees it.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Firecrawl tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Connect Firecrawl to Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Connect Firecrawl to ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web today. The plugin directory lives at chatgpt.com/plugins.

## Connect Firecrawl to Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Connect Firecrawl to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Only Read is granted by default, which is not enough to call a Firecrawl tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Firecrawl through Elaichi

### Research a prospect before the first call

Sales. Ask for a prospect's homepage, pricing page, and team page to be scraped and summarized so you walk into the call knowing what they sell and who runs it.

### Watch competitor pricing pages for changes

Marketing. Hand over a list of competitor pricing pages as one batch scrape and get back plan names, prices, and feature lists in a table you can compare week to week.

### Pull structured details from many pages

Product. Point an extract at a set of product or listing pages and get the same fields back for each one, such as name, price, and availability, ready to drop into a spreadsheet.

### Turn a help center into searchable text

Support. Crawl your own documentation site or a vendor's help center so an agent can answer customer questions from the current published pages instead of an old copy.

### Map every page on a site before an audit

Content. Get a map of every link on a site in one pass, then decide which pages to scrape, rewrite, or retire.

### Keep an eye on Firecrawl credit spend

Operations. Ask how many credits the team has used over the past weeks, check which crawls are still running, and stop a runaway crawl before it burns through the budget.

## Frequently asked questions

### How do I connect Firecrawl to Claude?

Connecting Firecrawl to Claude takes two steps. First, open Elaichi, choose Firecrawl, and paste in your Firecrawl API key; there is no OAuth app to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Sign in with your Elaichi account and Firecrawl is ready to use in your chats.

### Does Firecrawl work with ChatGPT and Cursor as well as Claude?

Yes. Once Firecrawl is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. You connect Firecrawl once and every client picks it up.

### What can an AI agent actually do with Firecrawl?

With Firecrawl connected, an agent can scrape a single web page into clean text, crawl an entire site, list every link on a site, or send a batch of pages to be scraped together. It can pull structured fields such as names, prices, and dates out of pages, open a browser session to work through a page that needs clicks, and check which crawls are still running or how many credits have been used. In practice that means asking in plain language for a competitor's pricing, a prospect's company overview, or a full copy of a help center, and getting the result back in the chat.

### Does connecting Firecrawl give the AI my whole Firecrawl account?

An agent working through Firecrawl can only do what the Firecrawl API key it was connected with allows, and Elaichi can narrow that further. Admins can restrict which actions are available, for example allowing scrapes and maps while blocking the ability to delete crawls or create browser sessions. Elaichi never widens what Firecrawl itself permits, and every request is written to an audit log with the name of the person who made it.

### Can my team share one Firecrawl connection?

Yes. One person connects Firecrawl in Elaichi with the API key, then shares the connection with a team, and nobody else ever sees or handles that key. Each teammate still signs in to Elaichi as themselves, so the audit log shows exactly who ran each scrape, crawl, or extract through the shared Firecrawl connection.

### Can I stop an agent from deleting or changing things in Firecrawl?

Yes. In Elaichi, restrictions on Firecrawl work per action, so you can block deleting crawls, batch scrapes, browser sessions, or agents while leaving scraping and crawling available. A blocked action is never shown to Claude, ChatGPT, Cursor, or any other client at all, so no prompt, however worded, can reach it.

### What happens to a Firecrawl connection when someone leaves?

When someone is offboarded in Elaichi, their access to Firecrawl through the endpoint ends immediately, in every client they had set up. If Firecrawl was connected as a shared connection, it keeps working for everyone else on the team. If you want to remove Firecrawl entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other connected client at the same time.

## All 30 Firecrawl tools

Every tool below is callable through https://api.elaichi.ai/mcp once Firecrawl is connected, subject to the toolbox it is in and the restrictions on the caller.

- **Get single Firecrawl agent by ID** (Get). Get the status of an agent job by job ID.
- **Create a Firecrawl agent** (Create). Start an agent task for agentic data extraction by providing a prompt and optional URLs, schema, and model configuration.
- **Delete a Firecrawl agent by ID** (Delete). Cancel an agent job by its job ID.
- **Get single Firecrawl batch scrape by ID** (Get). Get the status of a batch scrape job
- **Delete a Firecrawl batch scrape by ID** (Delete). Cancel a batch scrape job by its ID.
- **Create a Firecrawl batch scrape** (Create). Scrape multiple URLs in batch and optionally extract information using an LLM.
- **Firecrawl batch scrapes get errors** (Get). Get the errors of a batch scrape job
- **List all Firecrawl browsers** (List). List browser sessions, optionally filtered by status.
- **Create a Firecrawl browser** (Create). Create a browser session with configurable TTL, activity timeout, live view streaming, and optional persistent profile storage.
- **Firecrawl browsers execute** (Execute). Execute code in a browser session
- **Delete a Firecrawl browser by ID** (Delete). Delete a browser session by session ID.
- **Get single Firecrawl crawl by ID** (Get). Get the status of a crawl job
- **Delete a Firecrawl crawl by ID** (Delete). Cancel a crawl job by its ID.
- **Firecrawl crawls get errors** (Get). Get the errors of a crawl job
- **Create a Firecrawl crawl** (Create). Crawl multiple URLs starting from a base URL based on specified options such as depth, path filters, and concurrency limits.
- **Firecrawl crawls list active** (List). Get all active crawls for the authenticated team
- **Firecrawl crawls preview params** (Action). Preview crawl parameters generated from a natural language prompt describing what to crawl.
- **List all Firecrawl credit usage historicals** (List). Get historical credit usage for the authenticated team, optionally broken down by API key.
- **Create a Firecrawl extract** (Create). Extract structured data from pages using LLMs by providing URLs and an optional prompt, schema, and scrape options.
- **Get single Firecrawl extract by ID** (Get). Get the status of an extract job by its ID.
- **Create a Firecrawl map** (Create). Map multiple URLs from a base URL based on crawling and sitemap options.
- **Firecrawl scrapes delete interact** (Delete). Stop the interactive browser session associated with a scrape job.
- **Firecrawl scrapes interact** (Action). Interact with the browser session associated with a scrape job by executing code in the scrape-bound browser sandbox.
- **Create a Firecrawl scrape** (Create). Scrape a single URL and optionally extract information using an LLM.
- **List all Firecrawl searches** (List). Search the web and optionally scrape search results, with support for web, image, and news sources.
- **List all Firecrawl team activities** (List). Lists your team's recent API activity from the last 24 hours. Returns metadata about each job including the job ID, which can be used with the corresponding GET endpoint (e.g. GET /crawl/{id}) to retrieve full results. Supports cursor-based pagination and filtering by endpoint.
- **List all Firecrawl team credit usages** (List). Get remaining credits for the authenticated team
- **List all Firecrawl team queue status** (List). Retrieve metrics about your team's scrape queue, including job counts, concurrency limits, and most recent success timestamp.
- **List all Firecrawl team token usages** (List). Get remaining tokens for the authenticated team
- **List all Firecrawl token usage historicals** (List). Get historical token usage for the authenticated team (Extract only), optionally broken down by API key.