L
LinkFetch: LinkedIn MCP
Search LinkedIn jobs and companies, apply AI functions, and manage leads through a hosted MCP bridge.
Install LinkFetch: LinkedIn MCP
Pick your client, then add it in one click or paste the config.
~/Library/Application Support/Claude/claude_desktop_config.json{
"mcpServers": {
"linkfetch-linkedin-mcp": {
"command": "npx",
"args": [
"-y",
"linkfetch-mcp"
],
"env": {
"LINKFETCH_API_KEY": "YOUR_VALUE_HERE",
"LINKFETCH_MCP_URL": "YOUR_VALUE_HERE"
}
}
}
}
Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.
Values are written into the snippet above so you can paste it as is. They never leave your browser.
Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.
Overview
Use cases
- Search LinkedIn jobs by location or role
- Research companies and retrieve company records
- Score or classify jobs and companies with AI
- Save prospects and inspect lead lists
- Send LinkedIn messages or connection requests through a connected account
Key features
- Search and retrieve LinkedIn jobs
- Search and retrieve companies
- Run AI scoring, classification, extraction, and writing
- List and save leads
- Forward MCP calls through stdio or remote HTTP
- Support connected-account LinkedIn operations
How LinkFetch: LinkedIn MCP works
Tools11
What LinkFetch: LinkedIn MCP lets your agent do. Expand a tool for its parameters.
Security & health
What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.
ActiveLast checked Today
Recent health check succeeded.
Adoption & maintenance
Factual signals from GitHub, npm, and our automated checks — not a rating.
Last commit5d agoMost recent push to the default branch.
Tools exposed11Callable tools this server registers over MCP.
Reviews
No reviews yet — be the first to share how it worked for you.
Frequently Asked Questions about LinkFetch: LinkedIn MCP
LinkFetch: LinkedIn MCP is an MCP server that connects AI agents to LinkFetch’s hosted LinkedIn service through stdio or remote MCP. Its main tools search jobs and companies, retrieve records, run AI scoring, classification, extraction, and writing, and list or save leads. A connected LinkedIn account enables additional people, posts, inbox, messaging, and invitation operations.
Install it by configuring your MCP client to run `npx -y linkfetch-mcp` with `LINKFETCH_API_KEY` set to an `lf_...` key. Node.js 18 or later is required. Clients that support remote Streamable HTTP can connect directly to `https://linkfetch.io/mcp` instead.
Yes, LinkFetch: LinkedIn MCP works with Cursor through its MCP configuration. Add the `linkfetch-mcp` stdio command and `LINKFETCH_API_KEY` to `~/.cursor/mcp.json` or a project-level `.cursor/mcp.json` file.
`LINKFETCH_API_KEY` is required. Set it to an `lf_...` key from the LinkFetch MCP dashboard. `LINKFETCH_MCP_URL` is optional and can point the bridge to another LinkFetch MCP endpoint; it defaults to `https://linkfetch.io/mcp`.
No, a LinkedIn account is not needed for the jobs and companies tools. Account-based people, posts, inbox, messaging, invitations, and related operations require a connected LinkedIn account and remain subject to LinkFetch limits.
Related MCP servers
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.
AllMCPs Directory Badge
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
Badge Style:
Live Dynamic SVG Preview
Markdown (GitHub README)
[](https://allmcps.com/mcp/linkfetch-linkedin-mcp)HTML Embed
<a href="https://allmcps.com/mcp/linkfetch-linkedin-mcp"><img src="https://allmcps.com/api/badge/linkfetch-linkedin-mcp?style=directory" alt="LinkFetch: LinkedIn MCP on AllMCPs" /></a>