Firecrawl MCP

Live

API KEY

WEB DATA

Search

Every web page, crawl job, and extracted dataset your agent needs. Firecrawl MCP gives your agent authenticated access to web scraping and extraction scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the Firecrawl MCP account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: User permissions enforced. 90-day audit trail.
Firecrawl MCP
agent · Acme Q3
Run
Scrape the pricing pages of our top 5 competitors and extract their plan names and prices.
S
firecrawl_scrape
1.1s
Web data agent
5 pricing pages scraped. Extracted: Competitor A (Starter $29, Pro $79, Enterprise custom), Competitor B (Free, Growth $49, Scale $149), and 3 more with plan breakdowns.
Sources: 5 competitor pricing pages
firecrawlmcpmcp
5 pages
18:29
Message Claude...

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

CALL ANY TOOL
Scrape URLs, crawl sites, search and extract structured web content, and map sitemaps.
firecrawlmcp_firecrawl_map
Firecrawl map
Discover all indexed URLs on a website or within a URL subtree, with optional search filtering.
Parameters
Name
Type
Required
Description
url
string
Required
The URL of the page or website to scrape, crawl, or map.
ignoreQueryParameters
boolean
Optional
Set to true to treat URLs differing only by query string as duplicates.
includeSubdomains
boolean
Optional
Set to true to include subdomains of the target domain.
limit
number
Optional
Maximum number of results to return.
search
string
Optional
Search term to filter URLs returned by the map.
sitemap
string
Optional
How to use the sitemap: include to discover URLs from it, only to crawl only sitemap URLs, skip to ignore it.
firecrawlmcp_firecrawl_search
Firecrawl search
firecrawlmcp_firecrawl_agent
Firecrawl agent
firecrawlmcp_firecrawl_monitor_get
Firecrawl monitor get
firecrawlmcp_firecrawl_crawl
Firecrawl crawl
firecrawlmcp_firecrawl_monitor_run
Firecrawl monitor run
firecrawlmcp_firecrawl_parse
Firecrawl parse
firecrawlmcp_firecrawl_browser_list
Firecrawl browser list
firecrawlmcp_firecrawl_scrape
Firecrawl scrape
firecrawlmcp_firecrawl_monitor_list
Firecrawl monitor list
firecrawlmcp_firecrawl_extract
Firecrawl extract
firecrawlmcp_firecrawl_browser_create
Firecrawl browser create
firecrawlmcp_firecrawl_feedback
Firecrawl feedback
firecrawlmcp_firecrawl_browser_delete
Firecrawl browser delete
firecrawlmcp_firecrawl_interact
Firecrawl interact
firecrawlmcp_firecrawl_monitor_create
Firecrawl monitor create
firecrawlmcp_firecrawl_agent_status
Firecrawl agent status
firecrawlmcp_firecrawl_monitor_delete
Firecrawl monitor delete
firecrawlmcp_firecrawl_interact_stop
Firecrawl interact stop
firecrawlmcp_firecrawl_monitor_update
Firecrawl monitor update
firecrawlmcp_firecrawl_monitor_check
Firecrawl monitor check
firecrawlmcp_firecrawl_developer_search
Firecrawl developer search
firecrawlmcp_firecrawl_monitor_checks
Firecrawl monitor checks
firecrawlmcp_firecrawl_search_feedback
Firecrawl search feedback
firecrawlmcp_firecrawl_check_crawl_status
Firecrawl check crawl status
firecrawlmcp_firecrawl_research_read_paper
Firecrawl research read paper
firecrawlmcp_firecrawl_research_inspect_paper
Firecrawl research inspect paper
firecrawlmcp_firecrawl_research_search_github
Firecrawl research search github
firecrawlmcp_firecrawl_research_search_papers
Firecrawl research search papers
firecrawlmcp_firecrawl_research_related_papers
Firecrawl research related papers
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.
Python · LlamaIndex
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 });
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 }],
});
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.
GTM and RevOps Teams
Competitive intelligence briefing agent
Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.
GTM and RevOps Teams
Outbound prospecting agent
Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.
GTM and RevOps Teams
Deal intelligence agent
Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.
Support and Ops Teams
Support triage agent
Fetches new Zendesk tickets, classifies them by type and urgency, searches the Notion knowledge base for an answer, and routes what it cannot resolve to Slack. Every call runs on the support agent's own delegated OAuth.
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
Search Apollo for ICP matches, rank them, draft personalised Gmail outreach, and log every send to Google Sheets.
GTM
Competitive intelligence briefing agent
Scan Gong calls for competitor mentions, match each one to its Notion battlecard, and DM every affected rep a single Slack digest.
SALES
Deal intelligence agent
Score Gong call risk with an LLM, cross-reference the Attio record, and DM each owner their at-risk deals in Slack.
SUPPORT
Support triage agent
Classify new Zendesk tickets, search the Notion knowledge base for an answer, and route what it cannot resolve to Slack.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
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.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""firecrawlmcp"": {
""url"": ""https://mcp.scalekit.com/firecrawlmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.firecrawlmcp]
url = ""https://mcp.scalekit.com/firecrawlmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""firecrawlmcp"": {
""url"": ""https://mcp.scalekit.com/firecrawlmcp"",
""type"": ""http""
}
}
}