Atlas / MCP servers / fredericbarthelet / LinkedIn

LinkedInSAFE

mcp/fredericbarthelet/linkedin-6

An MCP Server for Linkedin API

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
2 1r · 1w · 0d
Transport
sse
License
—
Stars
40
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

MCP server for interacting with Linkedin Community Management API.

This MCP server:

⚠️ Disclaimer: The Third-Party Authorization Flow proposal status is currently in draft. The only MCP client, to my knowledge, that currently implements this specification of the protocol is the MCP Inspector

Features

Tools

  • user-info - Get current logged in user infos (name, headline and profile picture)
  • create-post - Create a new post on LinkedIn

Installation

Follow those instructions to run Linkedin MCP server on your host. You'll need to provide your own Linkedin client.

Requirements

  • Node 22 (lts/jod)
  • pnpm 10
  • a Linkedin client with Community Management API product installed and http://localhost:3001/callback added to the authorized redirect URLs

Instructions

  • Install dependencies:
pnpm install
  • Create env file and populate with your Linkedin client credentials and a random string secret value for JWT_SECRET:
cp .env.template .env && vi .env
  • Run the server:
pnpm run dev
  • Configure your favorite MCP client to use this new server:
{
"mcpServers": {
"linkedin": {
"url": "http://localhost:3001/sse"
}
}
}

Debugging

Start the MCP Inspector to debug this server, which is available as a

Read from source at commit c702e5934604OBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add linkedin-mcp-server --env JWT_SECRET=${JWT_SECRET} --env LINKEDIN_CLIENT_SECRET=${LINKEDIN_CLIENT_SECRET} -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "linkedin-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "JWT_SECRET": "${JWT_SECRET}",
        "LINKEDIN_CLIENT_SECRET": "${LINKEDIN_CLIENT_SECRET}"
      }
    }
  }
}
03

Exposed tools (2)

1 read · 1 write · 0 destructive.

ToolRiskDescription
create-postwriteCreate a new post on LinkedIn
user-inforeadGet information about currently logged in LinkedIn user
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (1 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (4)

LOWInventory / provenance · inv.hidden_file · CWE-1104
.cursorignore
.cursorignore
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.env.template
.env.template
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.no_license · CWE-1104
Why it matters. no LICENSE file and no repo licence
Fix. add a licence
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
axios, express, jsonwebtoken, linkedin-api-client, raw-body, vitest, zod, @types/express
Why it matters. 12 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass, no_license.

Audited 2026-10-08 · audit v0.4.1 · source sha c702e5934604full audit observations/trust-audit/mcp-server/fredericbarthelet__linkedin-6.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-08c702e5934604SAFEB89first audit
06

Questions

What is the LinkedIn MCP server?

An MCP Server for Linkedin API

What tools does LinkedIn expose?

2 in total: 1 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is LinkedIn safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does LinkedIn need?

It reads JWT_SECRET and LINKEDIN_CLIENT_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does LinkedIn run?

It speaks sse, so it runs as a service you connect to over the network. It is published on npm as linkedin-mcp-server at 0.1.0.

How current is this page?

The grade is for one exact copy of the source (c702e5934604), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement