Firecrawl MCP MCP | Api Key Firecrawl MCP connector for AI agents

CALL ANY TOOL

Scrape URLs, crawl sites, search and extract structured web content, and map sitemaps.

firecrawl_scrape

Scrape URL

Scrape a single URL and return cleaned markdown or structured content.

Parameters

Name

Type

Required

Description

url

string

Required

URL to scrape

formats

array

Optional

Output formats: markdown, html, screenshot

onlyMainContent

boolean

Optional

Strip nav, footer, and boilerplate

firecrawl_crawl

Crawl URL

firecrawl_crawl_status

Get crawl status

firecrawl_search

Search web

firecrawl_map

Map URL

Build your Agent

Drop the toolkit in, point it at the user, and your web data agent can use Firecrawl MCP from the first run.

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["firecrawlmcp"], toolNames: ["firecrawl_scrape", "firecrawl_crawl", "firecrawl_crawl_status"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["firecrawlmcp"], toolNames: ["firecrawl_scrape", "firecrawl_crawl", "firecrawl_crawl_status"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["firecrawlmcp"], toolNames: ["firecrawl_scrape", "firecrawl_crawl", "firecrawl_crawl_status"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

Copied

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/firecrawlmcp",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start using Firecrawl MCP.

Scrape & extract

Copy the prompt

Copied

Scrape [URL] and return the main content.

Copy the prompt

Copied

Extract all pricing info from [URL].

Copy the prompt

Copied

Scrape [URL] and output as markdown.

Copy the prompt

Copied

Get the text content of [URL] without boilerplate.

Crawl & map

Copy the prompt

Copied

Crawl [root URL] up to 3 pages deep.

Copy the prompt

Copied

Map all links on [URL].

Copy the prompt

Copied

Crawl [URL] and extract all product descriptions.

Copy the prompt

Copied

Get job status for crawl [job_id].

Search & research

Copy the prompt

Copied

Search the web for [query] and return content.

Copy the prompt

Copied

Find all pages on [domain] mentioning [topic].

Copy the prompt

Copied

Scrape the top 5 results for [query].

Copy the prompt

Copied

Extract contact info from [URL].

SEE HOW AUTH WORKS

Users authorize Firecrawl MCP once. Their credentials stay vaulted, every call is checked, and every action is logged.

1

Authorize

Your user connects

Firecrawl MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Firecrawl MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Firecrawl MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Firecrawl MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other web data agents and MCP connectors. Working code, live demos, fork what fits.

SALES

Outbound prospecting agent

Build targeted prospect lists with Apollo, enrich with firmographic data, and draft personalised outreach. Runs on a schedule.

Apollo

View agent

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Firecrawl MCP today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Firecrawl MCP as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Firecrawl MCP api key stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Firecrawl MCP?
Yes. Pass a tool name filter to listScopedTools so the web data agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Firecrawl MCP.

What happens when a user revokes Firecrawl MCP access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Are scraped pages cached or shared across tenants?
No cross-tenant caching. Each request uses the authorizing user's Firecrawl key. Rate limits and crawl credits apply per key; results are never shared across users in the vault.

Firecrawl MCP

Tools your web data agent reaches for on Firecrawl MCP, scoped per user.