Skip to main content
Glama
administrativetrick

LinkedIn Jobs MCP Server

LinkedIn Jobs MCP Server

A Model Context Protocol (MCP) server that enables Claude and other MCP clients to search LinkedIn jobs directly. Built with TypeScript and the official MCP SDK.

Features

  • πŸ” Advanced Job Search: Search LinkedIn jobs with multiple filters

  • 🎯 Smart Filtering: Filter by location, job type, experience level, salary, and more

  • ⚑ Fast & Reliable: Uses the proven linkedin-jobs-api package

  • πŸ”§ Easy Integration: Works with Claude Desktop, Claude Code, and any MCP-compatible client

Related MCP server: LinkedIn Job Search MCP Server

Installation

Prerequisites

  • Node.js 18 or higher

  • npm or yarn

Setup

  1. Clone or download this repository

cd linkedin-mcp-server
  1. Install dependencies

npm install
  1. Build the server

npm run build

Usage with Claude Desktop

Configure Claude Desktop

  1. Open your Claude Desktop configuration file:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

    • Windows: %APPDATA%\Claude\claude_desktop_config.json

  2. Add the server configuration:

{
  "mcpServers": {
    "linkedin-jobs": {
      "command": "node",
      "args": [
        "/ABSOLUTE/PATH/TO/linkedin-mcp-server/build/index.js"
      ]
    }
  }
}

Important: Replace /ABSOLUTE/PATH/TO/ with the actual path to your project directory.

  1. Restart Claude Desktop to load the new server

Using npx (Alternative)

You can also run the server using npx after publishing to npm:

{
  "mcpServers": {
    "linkedin-jobs": {
      "command": "npx",
      "args": [
        "-y",
        "linkedin-jobs-mcp-server"
      ]
    }
  }
}

Available Tools

search_linkedin_jobs

Search for jobs on LinkedIn with advanced filtering options.

Required Parameters:

  • keyword (string): Job title or keywords to search for

  • location (string): Location to search in (city, state, or "remote")

Optional Parameters:

  • dateSincePosted (enum): "past month", "past week", "24hr"

  • jobType (enum): "full time", "part time", "contract", "temporary", "volunteer", "internship"

  • remoteFilter (enum): "on site", "remote", "hybrid"

  • salary (enum): "40000", "60000", "80000", "100000", "120000" (minimum salary)

  • experienceLevel (enum): "internship", "entry level", "associate", "senior", "director", "executive"

  • limit (string): Number of results (1-100, default: "10")

  • sortBy (enum): "recent", "relevant"

  • page (string): Page number for pagination (default: "0")

Example Queries

Once configured, you can ask Claude things like:

"Search for software engineer jobs in San Francisco"

"Find remote product manager positions posted in the past week"

"Look for entry-level data analyst jobs in New York with a minimum salary of $80,000"

"Show me senior full-time positions for machine learning engineers in Seattle"

Example Response

Found 10 job(s) for "software engineer" in "San Francisco":

1. Senior Software Engineer
   Company: Tech Corp
   Location: San Francisco, CA
   Posted: 2 days ago
   Salary: $150,000 - $200,000
   Apply: https://linkedin.com/jobs/view/...

2. Full Stack Software Engineer
   Company: Startup Inc
   Location: San Francisco, CA (Hybrid)
   Posted: 1 week ago
   Apply: https://linkedin.com/jobs/view/...

...

Development

Build

npm run build

Watch mode (for development)

npm run watch

Test with MCP Inspector

The MCP Inspector is a useful tool for testing your server:

npm run inspector

This will open a web interface where you can test the server's tools interactively.

How It Works

This MCP server:

  1. Receives requests from Claude (or any MCP client) via the stdio transport

  2. Validates parameters using Zod schemas

  3. Calls the LinkedIn Jobs API (via linkedin-jobs-api package)

  4. Formats results into readable text responses

  5. Returns data back to the client

The server uses web scraping through the linkedin-jobs-api package, which accesses LinkedIn's public job listings. No authentication or API keys are required.

Architecture

Claude Desktop (MCP Client)
        ↓
    stdio transport
        ↓
LinkedIn MCP Server (This project)
        ↓
linkedin-jobs-api package
        ↓
LinkedIn public job listings

Troubleshooting

Server not appearing in Claude Desktop

  1. Check that the path in your config is absolute (not relative)

  2. Ensure the build directory exists (npm run build)

  3. Restart Claude Desktop completely

  4. Check Claude Desktop logs for errors

No results returned

  1. Try broader search terms

  2. Remove filters to see if you get results

  3. Check if LinkedIn has jobs for your search criteria

  4. Try different locations

Build errors

  1. Ensure you have Node.js 18+ installed

  2. Delete node_modules and build directories

  3. Run npm install again

  4. Run npm run build

Technical Details

  • MCP SDK Version: 1.0.4

  • Transport: stdio (standard input/output)

  • Language: TypeScript

  • Runtime: Node.js 18+

  • Data Source: LinkedIn public job listings (via linkedin-jobs-api)

Limitations

  • Rate limiting: The underlying API may have rate limits

  • Public data only: Only accesses publicly available job listings

  • No authentication: Does not require or support LinkedIn authentication

  • Scraping-based: Uses web scraping, which means it could break if LinkedIn changes their HTML structure

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License - feel free to use this in your own projects!

Support

If you encounter issues:

  1. Check the Troubleshooting section

  2. Review the MCP documentation at https://modelcontextprotocol.io

  3. Open an issue on GitHub with details about your problem

Acknowledgments

Available Tools

1 tool
search_linkedin_jobsA

Search for jobs on LinkedIn with advanced filtering options. Returns job listings with position titles, company names, locations, salary information, and application links.

ParametersJSON Schema
NameRequiredDescriptionDefault
keywordYesJob title or keywords to search for (e.g., 'software engineer', 'product manager')
locationYesLocation to search in (e.g., 'San Francisco', 'New York', 'remote')
dateSincePostedNoFilter by posting date
jobTypeNoType of employment
remoteFilterNoWork location type
salaryNoMinimum salary filter
experienceLevelNoRequired experience level
limitNoNumber of jobs to return (1-100, default: 10)
sortByNoSort results by recency or relevance
pageNoPage number for pagination (default: 0)

TDQS

A4/5.0
Behavior3/5

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

The description discloses the output fields but does not mention any behavioral aspects like side effects, authentication, or rate limits. Since no annotations are provided, the description should carry more burden; however, the output focus is adequate.

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?

Two concise sentences front-load the purpose and output. No unnecessary words.

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

Completeness4/5

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

For a search tool with detailed schema, the description covers purpose and output. Lacks mention of pagination or sorting defaults, but these are in schema. Overall complete given constraints.

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

Parameters3/5

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

All parameters have schema descriptions (100% coverage), so the description adds little beyond mentioning 'advanced filtering options.' Baseline 3 is appropriate.

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 the tool searches for jobs on LinkedIn with filtering options, using specific verbs and resource. No siblings exist, so differentiation is irrelevant.

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

Usage Guidelines4/5

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

The description implies usage for job search from LinkedIn, but does not explicitly state when to use or when not to use. With no sibling tools, the lack of exclusions is acceptable, making the context clear.

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

TDQS

A3.9/5.0
Disambiguation5/5

With only one tool, there is no possibility of ambiguity between tools. The tool's purpose is clearly described.

Naming Consistency5/5

The single tool name 'search_linkedin_jobs' follows a clear verb_noun pattern, which is consistent and descriptive.

Tool Count2/5

A single tool for a LinkedIn Jobs server is far too few. Expected tools for job details, applications, or filters are missing, making the server feel underdeveloped for its intended domain.

Completeness2/5

The tool set is severely incomplete, providing only search functionality. No tools for retrieving individual job details, applying, or managing job listings are present, leading to significant gaps.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that enables users to interact with LinkedIn feeds and search for job listings through natural language. It provides tools for retrieving recent feed posts and searching for professional opportunities based on specific keywords and locations.
    The Unlicense
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants to search LinkedIn jobs with built-in rate limiting to prevent IP bans. Supports job search, filtering, company profiles, and job categories through MCP tools.
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables job search on LinkedIn through MCP tools, including keyword and location search, filtering by remote, easy apply, experience level, job type, and date, and retrieving job details.
  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables searching real job listings from multiple job boards (Indeed, LinkedIn, Glassdoor, Google Jobs, etc.) through a single MCP tool, designed for use as a custom connector in Claude Cowork.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/administrativetrick/linkedin-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server