Application Development
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.
-
How it connects. Connects with an API key. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
30 tools
How to connect
How to connect Firecrawl to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Firecrawl once
-
Open Connections, choose Add connection, and pick Firecrawl.
-
Optionally set Share with to give a team access, then press Connect.
-
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.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Connect Firecrawl to Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
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
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
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
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Firecrawl to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Firecrawl through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Sales
Research a prospect before the first call
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.
-
Marketing
Watch competitor pricing pages for changes
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.
-
Product
Pull structured details from many pages
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.
-
Support
Turn a help center into searchable text
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.
-
Content
Map every page on a site before an audit
Get a map of every link on a site in one pass, then decide which pages to scrape, rewrite, or retire.
-
Operations
Keep an eye on Firecrawl credit spend
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.
Try asking
- “Which Firecrawl crawls returned errors this week?”
- “List batch scrapes created by the Docs team.”
- “Show browsers still running longer than an hour.”
AI tools
Firecrawl tools for your AI agents
30 tools are ready to call through Elaichi's MCP endpoint the moment you connect Firecrawl, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting Firecrawl gets you
6 screens from the product, each doing one job for your Firecrawl account.
The agent
Ask about crawls, get answers back.
Question your Firecrawl crawls, scrapes and browsers in plain language, answered from live records.
- crawls
- batch scrapes
- browsers
- agents
Ask Elaichi to work across your apps.
Which Firecrawl crawls returned errors this week?
List batch scrapes created by the Docs team.
Show browsers still running longer than an hour.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor reach Firecrawl.
One governed MCP endpoint over OAuth, no SDK and no shared API key.
ElaichiMCP clientsClaude
ChatGPT
Cursor
Copy the endpoint
Tool catalog
All 30 Firecrawl tools arrive ready.
Agents, batch scrapes, browsers and crawls exposed as tools, with no custom code.
- Get single Firecrawl agent by ID
- Create a Firecrawl agent
- Delete a Firecrawl agent by ID
- Get single Firecrawl batch scrape by ID
ElaichiToolsToolboxes
Every team gets its own toolbox.
Curate Firecrawl crawl and browser tools per team, scoped to the work they do.
- Engineering
- Data
- Docs
- Growth
ElaichiToolboxesShared connections
Teammates run crawls without seeing keys.
Each Firecrawl connection shows who connected it and which teams and members share it.
- Engineering
- Data Platform
- Docs Site
- Growth EMEA
ElaichiConnectionsAudit log
Every scrape and crawl call is recorded.
Append-only log of when, who, what happened, type and Firecrawl resource touched.
- When
- Who
- What happened
- Type
ElaichiAudit logLaunching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule fires, Firecrawl does the work.
Fetch crawls, group them, draft a digest, a person approves, post back.
Firecrawl digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch crawls
Firecrawl
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Firecrawl
Queued
Collections and dashboards
Firecrawl health, computed on a schedule.
Four metrics, 14 days of crawls created and a per team breakdown, no model involved.
Firecrawl health
Refreshed 4 minutes ago · every 15 minutes · from the crawls collection
Crawls
1,284 ↓ 12%
Batch scrapes
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Crawls created
Last 14 days
By team
Share of activity
Engineering 34%
Data Platform 27%
Docs Site 21%
Growth EMEA 18%
FAQ
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 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.
Put Firecrawl in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.