LinkedIn MCP Server

Instructions

Implementation Reference

• linkedin_mcp_server/tools/job.py:104-128 (handler)

  The async handler function that implements the core logic of get_recommended_jobs by using JobSearch scraper configured to fetch recommended jobs.

  async def get_recommended_jobs() -> List[Dict[str, Any]]:
      """
      Get your personalized recommended jobs from LinkedIn
  
      Returns:
          List[Dict[str, Any]]: List of recommended jobs
      """
      try:
          driver = safe_get_driver()
  
          logger.info("Getting recommended jobs")
          job_search = JobSearch(
              driver=driver,
              close_on_complete=False,
              scrape=True,  # Enable scraping to get recommended jobs
              scrape_recommended_jobs=True,
          )
  
          if hasattr(job_search, "recommended_jobs") and job_search.recommended_jobs:
              return [job.to_dict() for job in job_search.recommended_jobs]
          else:
              return []
      except Exception as e:
          return handle_tool_error_list(e, "get_recommended_jobs")

• linkedin_mcp_server/tools/job.py:96-103 (registration)

  The @mcp.tool decorator registers the get_recommended_jobs function as an MCP tool with appropriate annotations and metadata.

  @mcp.tool(
      annotations=ToolAnnotations(
          title="Get Recommended Jobs",
          readOnlyHint=True,
          destructiveHint=False,
          openWorldHint=True,
      )
  )

• linkedin_mcp_server/server.py:30-30 (registration)

  Invocation of register_job_tools which registers the job tools including get_recommended_jobs to the MCP server instance.

  register_job_tools(mcp)