What is linkedin-mcp CLAUDE.md?

Project instructions for an MCP server that reads and sends LinkedIn messages through a logged-in browser. It explains the browser-based connection, saved login session, main files, and messaging tools.

Use them when developing or debugging LinkedIn conversation tools, authentication, message retrieval, search, or pagination.

LinkedIn can block ordinary automated web requests, so these instructions document the required browser method and how login sessions are maintained. They help developers understand where messaging behavior is implemented.

How southleft/linkedin-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to southleft/linkedin-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/southleft/linkedin-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/southleft/linkedin-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/southleft/linkedin-mcp/claude-md.svg)](https://agentmods.dev/instructions/southleft/linkedin-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/southleft/linkedin-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/southleft/linkedin-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,045 This file is loaded in full into every session.

When invoked 1,045 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01045	$0.01045
Opus 5	$0.00522	$0.00522
Sonnet 5	$0.00209	$0.00209
Haiku 4.5	$0.00104	$0.00104

Measured 7d ago against content hash 21635cf1b0ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

linkedin-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LinkedIn MCP - Development Guide

Messaging / DM System

LinkedIn messaging uses a headless Playwright browser as the HTTP transport layer. This is required because LinkedIn's bot detection blocks all Python HTTP clients from accessing the Voyager API.

How it works

HeadlessLinkedInScraper.api_fetch() makes fetch() calls from within a real headless Chromium
Persistent session stored at ~/.linkedin-mcp/browser-session/
First use opens a visible browser for LinkedIn login (~30 seconds). After that, fully headless and automatic
Session lasts months. If expired, ensure_authenticated() auto-opens browser for re-login

Key files

src/linkedin_mcp/services/linkedin/headless_scraper.py — Browser transport with api_fetch() and ensure_authenticated()
src/linkedin_mcp/services/linkedin/client.py — LinkedInClient with GraphQL messaging methods
src/linkedin_mcp/server.py — MCP tool definitions

Messaging tools

get_conversations(limit, search) — List conversations with previews, unread counts, participant info
get_conversation(conversation_id, before_timestamp, count) — Read full message thread with pagination
search_conversations(query) — Search DMs by keyword or person name
reply_to_conversation(conversation_id, text, image_path) — Reply to any existing conversation, optionally with an image
send_message(recipients, text, image_path) — Send a message by profile public ID. Checks for existing conversations first, falls back to UI automation for new ones. Supports image attachments.

How sending works

For send_message with recipients: resolves the public ID to a name/URN, searches existing conversations for a match, and uses reply_to_conversation if found. For truly new conversations, uses Playwright UI automation (navigate to /messaging/thread/new/, type recipient, type message, click send).
For reply_to_conversation: navigates to the thread, then POSTs to voyagerMessagingDashMessengerMessages?action=createMessage with the conversation URN. If an image is attached, uses UI automation instead (sets file on hidden input, clicks send).
Image attachments: LinkedIn auto-uploads images when set on the hidden file input. The browser handles the upload and generates an assetUrn. The message is then sent with the asset reference in renderContentUnions.

Read the full file on GitHub · 67 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 67 lines · 1,045 tokens per session scan A 21635cf1b0ab

Subscribe to this mod's changes

linkedin-mcp CLAUDE.md is an instructions file published in the GitHub repository southleft/linkedin-mcp (41 stars, last pushed 1mo ago), licensed MIT. It adds 1,045 tokens to every session, about $0.0052 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Browser automation

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

linkedin-mcp: Instructions file for Claude Code