firecrawl-mcp 3.9.0 → 3.10.2

package/README.md

@@ -818,19 +818,23 @@ Check the status of an agent job and retrieve results when complete. Use this to
 
 ### 11. Browser Create (`firecrawl_browser_create`)
 
-Create a persistent cloud browser session for interactive automation.
+Create a cloud browser session for interactive automation.
 
 **Best for:**
 
 - Multi-step browser automation (navigate, click, fill forms, extract data)
 - Interactive workflows that require maintaining state across actions
 - Testing and debugging web pages in a live browser
+- Saving and reusing browser state with profiles
 
 **Arguments:**
 
 - `ttl`: Total session lifetime in seconds (30-3600, optional)
 - `activityTtl`: Idle timeout in seconds (10-3600, optional)
 - `streamWebView`: Whether to enable live view streaming (optional)
+- `profile`: Save and reuse browser state across sessions (optional)
+  - `name`: Profile name (sessions with the same name share state)
+  - `saveChanges`: Whether to save changes back to the profile (default: true)
 
 **Usage Example:**
 
@@ -838,7 +842,8 @@ Create a persistent cloud browser session for interactive automation.
 {
   "name": "firecrawl_browser_create",
   "arguments": {
-    "ttl": 600
+    "ttl": 600,
+    "profile": { "name": "my-profile", "saveChanges": true }
   }
 }
 ```

package/dist/index.js

@@ -142,43 +142,100 @@ const otherActions = [
 const allActionTypes = [...safeActionTypes, ...otherActions];
 // Use appropriate action types based on safe mode
 const allowedActionTypes = SAFE_MODE ? safeActionTypes : allActionTypes;
+function buildFormatsArray(args) {
+    const formats = args.formats;
+    if (!formats || formats.length === 0)
+        return undefined;
+    const result = [];
+    for (const fmt of formats) {
+        if (fmt === 'json') {
+            const jsonOpts = args.jsonOptions;
+            result.push({ type: 'json', ...jsonOpts });
+        }
+        else if (fmt === 'screenshot' && args.screenshotOptions) {
+            const ssOpts = args.screenshotOptions;
+            result.push({ type: 'screenshot', ...ssOpts });
+        }
+        else {
+            result.push(fmt);
+        }
+    }
+    return result;
+}
+function buildParsersArray(args) {
+    const parsers = args.parsers;
+    if (!parsers || parsers.length === 0)
+        return undefined;
+    const result = [];
+    for (const p of parsers) {
+        if (p === 'pdf' && args.pdfOptions) {
+            const pdfOpts = args.pdfOptions;
+            result.push({ type: 'pdf', ...pdfOpts });
+        }
+        else {
+            result.push(p);
+        }
+    }
+    return result;
+}
+function buildWebhook(args) {
+    const webhook = args.webhook;
+    if (!webhook)
+        return undefined;
+    const headers = args.webhookHeaders;
+    if (headers && Object.keys(headers).length > 0) {
+        return { url: webhook, headers };
+    }
+    return webhook;
+}
+function transformScrapeParams(args) {
+    const out = { ...args };
+    const formats = buildFormatsArray(out);
+    if (formats)
+        out.formats = formats;
+    const parsers = buildParsersArray(out);
+    if (parsers)
+        out.parsers = parsers;
+    delete out.jsonOptions;
+    delete out.screenshotOptions;
+    delete out.pdfOptions;
+    return out;
+}
 const scrapeParamsSchema = z.object({
     url: z.string().url(),
     formats: z
-        .array(z.union([
-        z.enum([
-            'markdown',
-            'html',
-            'rawHtml',
-            'screenshot',
-            'links',
-            'summary',
-            'changeTracking',
-            'branding',
-        ]),
-        z.object({
-            type: z.literal('json'),
-            prompt: z.string().optional(),
-            schema: z.record(z.string(), z.any()).optional(),
-        }),
-        z.object({
-            type: z.literal('screenshot'),
-            fullPage: z.boolean().optional(),
-            quality: z.number().optional(),
-            viewport: z
-                .object({ width: z.number(), height: z.number() })
-                .optional(),
-        }),
+        .array(z.enum([
+        'markdown',
+        'html',
+        'rawHtml',
+        'screenshot',
+        'links',
+        'summary',
+        'changeTracking',
+        'branding',
+        'json',
     ]))
         .optional(),
-    parsers: z
-        .array(z.union([
-        z.enum(['pdf']),
-        z.object({
-            type: z.enum(['pdf']),
-            maxPages: z.number().int().min(1).max(10000).optional(),
-        }),
-    ]))
+    jsonOptions: z
+        .object({
+        prompt: z.string().optional(),
+        schema: z.record(z.string(), z.any()).optional(),
+    })
+        .optional(),
+    screenshotOptions: z
+        .object({
+        fullPage: z.boolean().optional(),
+        quality: z.number().optional(),
+        viewport: z
+            .object({ width: z.number(), height: z.number() })
+            .optional(),
+    })
+        .optional(),
+    parsers: z.array(z.enum(['pdf'])).optional(),
+    pdfOptions: z
+        .object({
+        maxPages: z.number().int().min(1).max(10000).optional(),
+    })
         .optional(),
     onlyMainContent: z.boolean().optional(),
     includeTags: z.array(z.string()).optional(),
@@ -254,8 +311,8 @@ If JSON extraction returns empty, minimal, or just navigation content, the page
   "name": "firecrawl_scrape",
   "arguments": {
     "url": "https://example.com/api-docs",
-    "formats": [{
-      "type": "json",
+    "formats": ["json"],
+    "jsonOptions": {
       "prompt": "Extract the header parameters for the authentication endpoint",
       "schema": {
         "type": "object",
@@ -274,7 +331,7 @@ If JSON extraction returns empty, minimal, or just navigation content, the page
           }
         }
       }
-    }]
+    }
   }
 }
 \`\`\`
@@ -310,7 +367,8 @@ ${SAFE_MODE
     execute: async (args, { session, log }) => {
         const { url, ...options } = args;
         const client = getClient(session);
-        const cleaned = removeEmptyTopLevel(options);
+        const transformed = transformScrapeParams(options);
+        const cleaned = removeEmptyTopLevel(transformed);
         log.info('Scraping URL', { url: String(url) });
         const res = await client.scrape(String(url), {
             ...cleaned,
@@ -450,7 +508,11 @@ The query also supports search operators, that you can use if needed to refine t
     execute: async (args, { session, log }) => {
         const client = getClient(session);
         const { query, ...opts } = args;
-        const cleaned = removeEmptyTopLevel(opts);
+        const searchOpts = { ...opts };
+        if (searchOpts.scrapeOptions) {
+            searchOpts.scrapeOptions = transformScrapeParams(searchOpts.scrapeOptions);
+        }
+        const cleaned = removeEmptyTopLevel(searchOpts);
         log.info('Searching', { query: String(query) });
         const res = await client.search(query, {
             ...cleaned,
@@ -504,15 +566,8 @@ server.addTool({
         ...(SAFE_MODE
             ? {}
             : {
-                webhook: z
-                    .union([
-                    z.string(),
-                    z.object({
-                        url: z.string(),
-                        headers: z.record(z.string(), z.string()).optional(),
-                    }),
-                ])
-                    .optional(),
+                webhook: z.string().optional(),
+                webhookHeaders: z.record(z.string(), z.string()).optional(),
             }),
         deduplicateSimilarURLs: z.boolean().optional(),
         ignoreQueryParameters: z.boolean().optional(),
@@ -521,7 +576,15 @@ server.addTool({
     execute: async (args, { session, log }) => {
         const { url, ...options } = args;
         const client = getClient(session);
-        const cleaned = removeEmptyTopLevel(options);
+        const opts = { ...options };
+        if (opts.scrapeOptions) {
+            opts.scrapeOptions = transformScrapeParams(opts.scrapeOptions);
+        }
+        const webhook = buildWebhook(opts);
+        if (webhook)
+            opts.webhook = webhook;
+        delete opts.webhookHeaders;
+        const cleaned = removeEmptyTopLevel(opts);
         log.info('Starting crawl', { url: String(url) });
         const res = await client.crawl(String(url), {
             ...cleaned,
@@ -750,21 +813,26 @@ Check the status of an agent job and retrieve results when complete. Use this to
 server.addTool({
     name: 'firecrawl_browser_create',
     description: `
-Create a persistent browser session for code execution via CDP (Chrome DevTools Protocol).
+Create a browser session for code execution via CDP (Chrome DevTools Protocol).
 
-**Best for:** Running code (Python/JS) that interacts with a live browser page, multi-step browser automation, persistent sessions that survive across multiple tool calls.
+**Best for:** Running code (Python/JS) that interacts with a live browser page, multi-step browser automation, sessions with profiles that survive across multiple tool calls.
 **Not recommended for:** Simple page scraping (use firecrawl_scrape instead).
 
 **Arguments:**
 - ttl: Total session lifetime in seconds (30-3600, optional)
 - activityTtl: Idle timeout in seconds (10-3600, optional)
 - streamWebView: Whether to enable live view streaming (optional)
+- profile: Save and reuse browser state (cookies, localStorage) across sessions (optional)
+  - name: Profile name (sessions with the same name share state)
+  - saveChanges: Whether to save changes back to the profile (default: true)
 
 **Usage Example:**
 \`\`\`json
 {
   "name": "firecrawl_browser_create",
-  "arguments": {}
+  "arguments": {
+    "profile": { "name": "my-profile", "saveChanges": true }
+  }
 }
 \`\`\`
 **Returns:** Session ID, CDP URL, and live view URL.
@@ -773,6 +841,10 @@ Create a persistent browser session for code execution via CDP (Chrome DevTools
         ttl: z.number().min(30).max(3600).optional(),
         activityTtl: z.number().min(10).max(3600).optional(),
         streamWebView: z.boolean().optional(),
+        profile: z.object({
+            name: z.string().min(1).max(128),
+            saveChanges: z.boolean().default(true),
+        }).optional(),
     }),
     execute: async (args, { session, log }) => {
         const client = getClient(session);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "firecrawl-mcp",
-  "version": "3.9.0",
+  "version": "3.10.2",
   "description": "MCP server for Firecrawl web scraping integration. Supports both cloud and self-hosted instances. Features include web scraping, search, batch processing, structured data extraction, and LLM-powered content analysis.",
   "type": "module",
   "mcpName": "io.github.firecrawl/firecrawl-mcp-server",