How to Use the Firecrawl MCP in LlamaIndex

Q: Can LlamaIndex chunk the Markdown returned by Firecrawl?

Yes, the output from scrapepage is standard Markdown. LlamaIndex node parsers handle this format natively, splitting the content by headers to maintain semantic structure.

Q: How does the Firecrawl search tool help LlamaIndex avoid hallucinations?

The searchweb tool pulls live, scraped page content from the top search results. LlamaIndex uses this fresh data to ground its responses, ensuring it relies on current facts rather than outdated model weights.

Q: Can I limit which tools the LlamaIndex agent can access?

Yes, you can use the allowedtools filter when configuring your MCP client. This allows you to expose only scrapepage while restricting deeper crawling operations.

Feed clean web Markdown directly into LlamaIndex vector stores for hallucination-free RAG.

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

Index Clean Markdown directly into LlamaIndex

Stop feeding raw, noisy HTML into your vector index. Use `scrape_page` to extract clean, structured Markdown that LlamaIndex can parse and chunk without wasting embedding tokens on header scripts or cookie notices. This clean formatting ensures that your semantic search queries yield highly relevant chunks. Your RAG pipelines get grounded in actual page content rather than code noise.

Map Site Structures for RAG Ingestion

Before indexing an entire domain, your LlamaIndex agent can run `map_site` to discover every available URL. This gives the indexer a clear list of target pages to ingest systematically. You can filter this sitemap to target high-signal directories. This prevents your knowledge base from being polluted with irrelevant pages or redundant links.

Dynamic Web Research via MCP Server Tools

Give your LlamaIndex agent the ability to execute real-time research using these MCP tools. When a user query requires fresh data, the agent searches the web with `search_web` and crawls the top results with `crawl_site` on the fly. The scraped Markdown from these search results is converted into temporary index nodes. This allows your agent to answer time-sensitive questions with grounded, real-time facts.

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

Install llama-index-tools-mcp and instantiate the MCP client with your Vinkius endpoint. Wrap it in McpToolSpec and call to_tool_list_async to pass the tools to your FunctionAgent.

Yes, the output from `scrape_page` is standard Markdown. LlamaIndex node parsers handle this format natively, splitting the content by headers to maintain semantic structure.

The `search_web` tool pulls live, scraped page content from the top search results. LlamaIndex uses this fresh data to ground its responses, ensuring it relies on current facts rather than outdated model weights.

Yes, you can use the allowed_tools filter when configuring your MCP client. This allows you to expose only `scrape_page` while restricting deeper crawling operations.

All scraped DOM structures, Markdown outputs, and URL paths are processed in isolated, ephemeral environments. Your extraction requests and target site data are never cached or exposed to external networks.

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