Skip to main content
Glama
NYO2008

Firecrawl MCP Server

by NYO2008

firecrawl_search

Search the web for specific information and extract content from results to find relevant data across multiple websites.

Instructions

Search the web and optionally extract content from search results.

Best for: Finding specific information across multiple websites, when you don't know which website has the information; when you need the most relevant content for a query. Not recommended for: When you already know which website to scrape (use scrape); when you need comprehensive coverage of a single website (use map or crawl). Common mistakes: Using crawl or map for open-ended questions (use search instead). Prompt Example: "Find the latest research papers on AI published in 2023." Usage Example:

{
  "name": "firecrawl_search",
  "arguments": {
    "query": "latest AI research papers 2023",
    "limit": 5,
    "lang": "en",
    "country": "us",
    "scrapeOptions": {
      "formats": ["markdown"],
      "onlyMainContent": true
    }
  }
}

Returns: Array of search results (with optional scraped content).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query string
limitNoMaximum number of results to return (default: 5)
langNoLanguage code for search results (default: en)
countryNoCountry code for search results (default: us)
tbsNoTime-based search filter
filterNoSearch filter
locationNoLocation settings for search
scrapeOptionsNoOptions for scraping search results

Implementation Reference

  • The handler function for the 'firecrawl_search' tool. Validates input with isSearchOptions, performs the search using the Firecrawl client, formats the results including URLs, titles, descriptions, and optional markdown content, and handles errors.
          case 'firecrawl_search': {
            if (!isSearchOptions(args)) {
              throw new Error('Invalid arguments for firecrawl_search');
            }
            try {
              const response = await withRetry(
                async () =>
                  client.search(args.query, { ...args, origin: 'mcp-server' }),
                'search operation'
              );
    
              if (!response.success) {
                throw new Error(
                  `Search failed: ${response.error || 'Unknown error'}`
                );
              }
    
              // Format the results
              const results = response.data
                .map(
                  (result) =>
                    `URL: ${result.url}
    Title: ${result.title || 'No title'}
    Description: ${result.description || 'No description'}
    ${result.markdown ? `\nContent:\n${result.markdown}` : ''}`
                )
                .join('\n\n');
    
              return {
                content: [{ type: 'text', text: trimResponseText(results) }],
                isError: false,
              };
            } catch (error) {
              const errorMessage =
                error instanceof Error
                  ? error.message
                  : `Search failed: ${JSON.stringify(error)}`;
              return {
                content: [{ type: 'text', text: trimResponseText(errorMessage) }],
                isError: true,
              };
            }
          }
  • The Tool definition for 'firecrawl_search' including name, detailed description, and comprehensive inputSchema specifying parameters like query, limit, lang, country, scrapeOptions, etc.
    const SEARCH_TOOL: Tool = {
      name: 'firecrawl_search',
      description: `
    Search the web and optionally extract content from search results.
    
    **Best for:** Finding specific information across multiple websites, when you don't know which website has the information; when you need the most relevant content for a query.
    **Not recommended for:** When you already know which website to scrape (use scrape); when you need comprehensive coverage of a single website (use map or crawl).
    **Common mistakes:** Using crawl or map for open-ended questions (use search instead).
    **Prompt Example:** "Find the latest research papers on AI published in 2023."
    **Usage Example:**
    \`\`\`json
    {
      "name": "firecrawl_search",
      "arguments": {
        "query": "latest AI research papers 2023",
        "limit": 5,
        "lang": "en",
        "country": "us",
        "scrapeOptions": {
          "formats": ["markdown"],
          "onlyMainContent": true
        }
      }
    }
    \`\`\`
    **Returns:** Array of search results (with optional scraped content).
    `,
      inputSchema: {
        type: 'object',
        properties: {
          query: {
            type: 'string',
            description: 'Search query string',
          },
          limit: {
            type: 'number',
            description: 'Maximum number of results to return (default: 5)',
          },
          lang: {
            type: 'string',
            description: 'Language code for search results (default: en)',
          },
          country: {
            type: 'string',
            description: 'Country code for search results (default: us)',
          },
          tbs: {
            type: 'string',
            description: 'Time-based search filter',
          },
          filter: {
            type: 'string',
            description: 'Search filter',
          },
          location: {
            type: 'object',
            properties: {
              country: {
                type: 'string',
                description: 'Country code for geolocation',
              },
              languages: {
                type: 'array',
                items: { type: 'string' },
                description: 'Language codes for content',
              },
            },
            description: 'Location settings for search',
          },
          scrapeOptions: {
            type: 'object',
            properties: {
              formats: {
                type: 'array',
                items: {
                  type: 'string',
                  enum: ['markdown', 'html', 'rawHtml'],
                },
                description: 'Content formats to extract from search results',
              },
              onlyMainContent: {
                type: 'boolean',
                description: 'Extract only the main content from results',
              },
              waitFor: {
                type: 'number',
                description: 'Time in milliseconds to wait for dynamic content',
              },
            },
            description: 'Options for scraping search results',
          },
        },
        required: ['query'],
      },
    };
  • src/index.ts:955-966 (registration)
    Registration of all tools including SEARCH_TOOL in the listTools request handler.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: [
        SCRAPE_TOOL,
        MAP_TOOL,
        CRAWL_TOOL,
        CHECK_CRAWL_STATUS_TOOL,
        SEARCH_TOOL,
        EXTRACT_TOOL,
        DEEP_RESEARCH_TOOL,
        GENERATE_LLMSTXT_TOOL,
      ],
    }));
  • Type guard helper function to validate arguments for firecrawl_search tool.
    function isSearchOptions(args: unknown): args is SearchOptions {
      return (
        typeof args === 'object' &&
        args !== null &&
        'query' in args &&
        typeof (args as { query: unknown }).query === 'string'
      );
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description carries the full burden. It explains the return type (array of search results with optional scraped content) and includes parameters like time filter and location, but does not explicitly state it is non-destructive, which is minor.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-organized with clear sections (Best for, Not recommended for, Common mistakes, Prompt Example, Usage Example, Returns) and no unnecessary words. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (8 parameters, nested objects, no output schema), the description covers the purpose, usage, parameters, and return type adequately. It includes examples and guidance, making it complete for effective tool selection and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are already documented. The description adds value with a usage example and contextual grouping (e.g., scrapeOptions), improving understanding beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it searches the web and optionally extracts content. It distinguishes from siblings like scrape, map, and crawl by providing specific use cases (Best for, Not recommended for).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance is given on when to use (Best for) and when not to use (Not recommended for), along with common mistakes and a detailed usage example, making it easy for an AI agent to decide correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.