search

MCP tool from Firecrawl MCP Server by firecrawl

Web search for info

How to use it

search is exposed by the Firecrawl MCP Server MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the search tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Firecrawl MCP Server

$npx -y @smithery/cli install @mendableai/mcp-server-firecrawl --client claude

FULL FIRECRAWL MCP SERVER LISTING

Other tools in Firecrawl MCP Server (29)

Complex multi-source research

Research finished - response includes the extracted data

Multi-page extraction (with limits)

Programming questions over developer sources

An error occurred

firecrawl_monitor_check

get page-level results, including diff, snapshot, judgment.meaningful, and judgment.meaningfulChanges.

firecrawl_monitor_checks

list checks, optionally filtered by status.

firecrawl_monitor_delete

delete a monitor (destructive; only call when the user intends to remove it).

firecrawl_monitor_get

get one monitor.

firecrawl_monitor_list

list monitors.

firecrawl_monitor_run

trigger a check now.

firecrawl_monitor_update

update fields including goal, judgeEnabled, webhook, and notification.

firecrawl_research_inspect_paper

retrieve canonical metadata for one paper ID (arXiv, PMC, PMID, or DOI).

firecrawl_research_read_paper

read full-text passages from a specific paper.

firecrawl_research_related_papers

expand from one or more anchor papers through the citation graph.

firecrawl_research_search_github

search indexed public GitHub issue, pull-request, and README content.

firecrawl_research_search_papers

search paper metadata and abstracts with a natural-language query, with optional author, category, and date filters.

Interact with a URL or scraped page

Discovering URLs on a site

Recurring page checks

Files and hosted upload refs

Agent is still researching - check back later

Natural language description of the data you want (required, max 10,000 characters)

(required): the developer question or search phrase.

Paper and GitHub repository research

Optional JSON schema for structured output

Single page content

set to "only" to search agent-skill files alone.

Optional array of URLs to focus the agent on specific pages