docs(saved-jobs): add docs, expose max_pages, use Set in JS dedup

Address Greptile review: use Set for O(1) dedup in _EXTRACT_JOB_IDS_JS,
expose max_pages parameter on get_saved_jobs MCP tool, and document the
new tool in AGENTS.md, README.md, and docs/docker-hub.md.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: IfThingsThenStuff

README.md

@@ -52,6 +52,7 @@ What has Anthropic been posting about recently? https://www.linkedin.com/company
 | `search_jobs` | Search for jobs with keywords and location filters | working |
 | `search_people` | Search for people by keywords and location | working |
 | `get_job_details` | Get detailed information about a specific job posting | working |
+| `get_saved_jobs` | Get saved/bookmarked jobs from your LinkedIn job tracker | working |
 | `close_session` | Close browser session and clean up resources | working |
 
 > [!IMPORTANT]

docs/docker-hub.md

@@ -9,6 +9,7 @@ A Model Context Protocol (MCP) server that connects AI assistants to LinkedIn. A
 - **Company Profiles**: Extract comprehensive company data
 - **Job Details**: Retrieve job posting information
 - **Job Search**: Search for jobs with keywords and location filters
+- **Saved Jobs**: Get saved/bookmarked jobs from your LinkedIn job tracker
 - **People Search**: Search for people by keywords and location
 - **Person Posts**: Get recent activity/posts from a person's profile
 - **Company Posts**: Get recent posts from a company's LinkedIn feed

linkedin_mcp_server/scraping/extractor.py

@@ -2078,10 +2078,11 @@ async def search_jobs(
         return result
 
     _EXTRACT_JOB_IDS_JS = """() => {
+        const seen = new Set();
         const ids = [];
         document.querySelectorAll('a[href*="/jobs/view/"]').forEach(a => {
             const match = a.href.match(/\\/jobs\\/view\\/(\\d+)/);
-            if (match && !ids.includes(match[1])) ids.push(match[1]);
+            if (match && !seen.has(match[1])) { seen.add(match[1]); ids.push(match[1]); }
         });
         return ids;
     }"""