Clawy MCP Server

Instructions

Implementation Reference

• src/tools/firecrawl.ts:5-16 (registration)

  Definition and registration of the 'firecrawl_scrape' tool.

  {
    name: "firecrawl_scrape",
    description: "Scrape a single URL and extract clean, structured content. Handles JavaScript rendering and bypasses common blocks. Returns markdown optimized for LLMs.",
    inputSchema: z.object({
      url: z.string().describe("URL to scrape"),
      formats: z.array(z.enum(["markdown", "html", "rawHtml", "links", "screenshot"])).optional()
        .describe("Output formats (default: ['markdown'])"),
      onlyMainContent: z.boolean().optional().describe("Extract only main content, skip nav/footer (default true)"),
      waitFor: z.number().optional().describe("Wait milliseconds for JS rendering"),
    }),
    endpoint: "/v1/firecrawl/scrape",
  },

• src/index.ts:14-39 (handler)

  The generic handler for all registered tools, including firecrawl_scrape. It uses gatewayRequest to fetch data from the API endpoint defined in tool configurations.

  // Register all tools
  for (const tool of allTools) {
    server.tool(
      tool.name,
      tool.description,
      tool.inputSchema.shape,
      async (params) => {
        const method = tool.method || "POST";
        const result = await gatewayRequest(method, tool.endpoint, params as Record<string, unknown>);
  
        if (result.error) {
          return {
            content: [{ type: "text" as const, text: `Error (${result.status}): ${result.error}` }],
            isError: true,
          };
        }
  
        const text = typeof result.data === "string"
          ? result.data
          : JSON.stringify(result.data, null, 2);
  
        return {
          content: [{ type: "text" as const, text }],
        };
      },
    );