How to Use the Firecrawl MCP in LlamaIndex

Q: Can I map a site before indexing it with LlamaIndex and Firecrawl?

Yes, your LlamaIndex agent can run mapwebsitestructure first to get a clean list of URLs. This lets you filter out irrelevant paths before triggering a crawl, saving index storage and API credits.

Q: How do I monitor background crawls in LlamaIndex using Firecrawl?

Your agent can poll getcrawlstatus using the job ID returned by startcrawl. Once the status shows the crawl is finished, LlamaIndex can pull the entire dataset and rebuild the vector index.

Q: Does the crawler handle client-side JavaScript?

Yes, when you trigger scrapeurl or startcrawl, the underlying engine renders all dynamic JavaScript. Your agent gets the fully hydrated page content as clean markdown.

Index clean markdown from any website directly into your LlamaIndex vector store using this Firecrawl MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Firecrawl MCP to LlamaIndex

Create your Vinkius account to connect Firecrawl to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Firecrawl with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed clean web markdown to LlamaIndex RAG pipelines

LlamaIndex works best when its ingestion pipeline receives clean data. By calling `scrape_url` through this MCP Server, your agent pulls clean markdown from JS-heavy sites directly into your document nodes, bypassing noisy HTML boilerplate. Instead of indexing messy headers and footers that pollute your vector embeddings, you store only high-signal content. This directly improves retrieval accuracy when your RAG pipeline queries the index.

Map and index entire sites recursively

You can build a complete knowledge base of a target domain by combining LlamaIndex with Firecrawl's discovery tools. Your agent calls `map_website_structure` to find every valid link, then feeds those URLs into `start_crawl` to fetch the entire site. As the crawl progresses, your agent checks `get_crawl_status` to pull down completed pages in batches. LlamaIndex indexes these batches on the fly, keeping your local vector store updated with fresh web data.

Track scraping costs inside your index workflows

Running massive web ingestion pipelines can get expensive quickly. This server lets your LlamaIndex agent call `get_api_usage` before starting a massive crawl, letting you set hard budget guardrails in your Python script. If a crawl is consuming too many credits or getting stuck on infinite scroll pages, your agent can issue a `cancel_active_crawl` command. This keeps your indexing costs predictable and prevents runaway API bills.

Setup guide

Set up Firecrawl MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Firecrawl MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Firecrawl tools.",
)
response = await agent.run("List recent Firecrawl data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Firecrawl. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Firecrawl now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Firecrawl MCP in LlamaIndex

You register the server with the LlamaIndex MCP tool spec, which exposes the scraping tools to your agent. When the agent calls `scrape_url`, the returned markdown is packed into a LlamaIndex Document object for immediate chunking and indexing.

Yes, your LlamaIndex agent can run `map_website_structure` first to get a clean list of URLs. This lets you filter out irrelevant paths before triggering a crawl, saving index storage and API credits.

Your agent can poll `get_crawl_status` using the job ID returned by `start_crawl`. Once the status shows the crawl is finished, LlamaIndex can pull the entire dataset and rebuild the vector index.

Yes, when you trigger `scrape_url` or `start_crawl`, the underlying engine renders all dynamic JavaScript. Your agent gets the fully hydrated page content as clean markdown.

The scraped HTML, markdown, and URL metadata are processed in isolated, ephemeral memory blocks. Your data is never persisted on Vinkius, ensuring your target site extraction remains completely private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript