toolgate-firecrawl-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@toolgate-firecrawl-mcp scrape https://example.com for me"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
toolgate-firecrawl-mcp
A recoverable Firecrawl MCP server powered by Toolgate.
Every paid scrape goes through a full lifecycle: balance check → execute → charge → trace. If it fails, you get a refund or fallback — never a silent loss.
What happens when you scrape
Agent calls scrape_url
→ Toolgate checks idempotency (duplicate? return cached)
→ Toolgate checks balance (enough? deduct $0.10)
→ Firecrawl scrapes the URL (JS-rendered, clean markdown)
→ On success: charge confirmed, trace saved
→ On failure: refund issued, trace saved with reason
→ On no balance: fallback (fetch+cheerio metadata) returned freeRelated MCP server: webcrawl-mcp
Quick Start
Install & run (demo mode — no API key needed)
npm install
npm run devDemo mode uses fetch+cheerio as the scraping backend. scrape_url and balance tools work out of the box. No Firecrawl credits consumed.
Claude Desktop — demo mode
{
"mcpServers": {
"toolgate-firecrawl": {
"command": "node",
"args": ["/path/to/toolgate-firecrawl-mcp/dist/server.js"],
"env": {
"TOOLGATE_DEMO_MODE": "true"
}
}
}
}Claude Desktop — production (real Firecrawl)
{
"mcpServers": {
"toolgate-firecrawl": {
"command": "node",
"args": ["/path/to/toolgate-firecrawl-mcp/dist/server.js"],
"env": {
"FIRECRAWL_API_KEY": "fc-your-key-here"
}
}
}
}Tools
Tool | Price | Description |
| $0.10/call | Scrape a URL → clean markdown. Fallback: basic metadata free. |
| $0.01/result (min $0.05) | Web search via Firecrawl. Requires API key. |
| $0.15/call | Structured JSON extraction with schema. Requires API key. |
| free | Check your current Toolgate balance. |
| free | Add demo balance (demo mode only). |
| free | View recent execution traces with decisions and charge status. |
Demo
npm run scenarioExample output:
{
"passed": 6,
"failed": 0,
"skipped": 2,
"scenarios": [
{ "name": "url_validation_ssrf", "passed": true },
{ "name": "payment_missing_fallback", "passed": true },
{ "name": "credit_balance", "passed": true },
{ "name": "paid_scrape", "passed": true },
{ "name": "duplicate_request", "passed": true },
{ "name": "unreachable_url", "skipped": true, "reason": "network" },
{ "name": "free_tier_not_applicable", "passed": true },
{ "name": "trace_output", "passed": true }
]
}How Toolgate works here
Toolgate wraps every Firecrawl call with a payment lifecycle. Each call gets an idempotency key — retrying with the same key returns the cached result at no extra cost. If the Firecrawl call fails after payment was deducted, the charge is automatically refunded. Every decision is recorded in a queryable execution trace.
Environment Variables
Variable | Default | Description |
| — | Firecrawl API key. Omit for demo mode. |
|
| Firecrawl API base URL. |
|
| Toolgate publisher key. |
|
| Force demo mode. |
|
| USD pre-loaded in demo mode. |
|
| Timeout for scrape requests. |
|
| Max response size. |
Built with
@tkorkmaz/toolgate — paid-action runtime
@mendable/firecrawl-js — scraping engine
@modelcontextprotocol/sdk — MCP server/client
License
MIT
Available Tools
4 toolsadd_balanceA
Add demo balance to your Toolgate account (demo mode only).
Inputs: amount (required).
check_balanceA
Check your current Toolgate balance for this MCP session.
Inputs: no named parameters.
scrape_urlA
Scrape a URL and return its markdown content. Paid via Toolgate — includes idempotency, fallback, and refund on failure. [Pricing: $0.1/call] [Has free basic mode]
Inputs: url (required), requestId.
view_tracesA
View recent Toolgate execution traces for this session (lifecycle, decisions, charge status).
Inputs: limit, caller_id.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a distinct purpose: adding demo balance, checking balance, scraping URLs, and viewing traces. No overlaps or ambiguous boundaries.
All tool names follow a consistent verb_noun pattern in snake_case (add_balance, check_balance, scrape_url, view_traces), making them predictable and easy to understand.
With 4 tools covering balance management, scraping, and tracing, the count is well-scoped for a focused MCP server without unnecessary bloat.
The tool set covers core operations (balance add/check, scrape, view traces). Minor gap: no tool for configuring or resetting the session, but not critical for the demo purpose.
Maintenance
Related MCP Connectors
Scrape, crawl, and search the web via Firecrawl’s official hosted MCP.
Programmatic web-scraping MCP server powered by x402 micro-transactions on Base.
Zenrows MCP server: Fetch, Extract, Batch, and Browser Sessions for AI agents
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
Related MCP Servers
- AlicenseAqualityCmaintenanceMCP server for web scraping — extract clean markdown, links, and metadata from any URL. Free Firecrawl alternative.5102 npm6MIT
- AlicenseBqualityCmaintenanceLightweight MCP server for web scraping, search, and crawling. Uses local trafilatura/DuckDuckGo by default with optional Firecrawl fallback for transport-blocked pages.416MIT
- AlicenseNot gradedqualityCmaintenanceWeb scraping and search MCP server that wraps Firecrawl API for URL discovery and web search with optional content retrieval.165 npm1MIT
- AlicenseAqualityDmaintenanceA Firecrawl MCP server with built-in support for multiple API key rotation, enabling web search, scraping, crawling, extraction, and more via MCP clients.263MIT