linkedin-mcp AGENTS.md

An MCP server that lets AI tools access LinkedIn through structured data, using your logged-in browser session.

In plain words
What is it for?
It helps search people, jobs, companies, and company employees; view profiles, job details, company posts, and feeds; and handle supported LinkedIn interactions.
Why use it?
It avoids manually switching between LinkedIn and an AI coding tool for profile, job, company, feed, and messaging tasks. Actions that change LinkedIn data require explicit confirmation and are subject to safety limits.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/devag7/linkedin-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/devag7/linkedin-mcp

Made for: Codex, OpenCode.

Per session 582 This file is loaded in full into every session.
When invoked 582 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00582 $0.00582
Opus 5 $0.00291 $0.00291
Sonnet 5 $0.00116 $0.00116
Haiku 4.5 $0.00058 $0.00058

Measured 2d ago against content hash 07abe4be1a9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

linkedin-mcp AGENTS.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 2d 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.

AGENTS.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI agents using or contributing to LinkedIn MCP (linkedin-mcp-tools).

What this is

An MCP server exposing LinkedIn to any MCP client (Claude, Cursor, …) as structured JSON. It drives a real stealth Chrome to pass Cloudflare, then calls LinkedIn's Voyager API from inside the authenticated page. 22 tools.

Using it (as an agent / MCP client)

  1. The human runs the one-time login: npx -y linkedin-mcp-tools@latest --login.
  2. Configure the MCP server: command npx, args ["-y","linkedin-mcp-tools@latest"].
  3. Call tools. Reads return structured JSON. Writes require confirm: true and count against daily safety caps — only call them when the user explicitly asks, and surface the returned status (ok / duplicate / already_connected / restricted / quota_exhausted / not_allowed / failed) back to the user.
  4. Check health_check if a call fails — it reports login state, a live API probe, and remaining daily budget.

Tool map

  • Profiles: get_my_profile, get_profile
  • Search: search_people, search_jobs, get_job_details, search_companies, get_company, get_company_posts, get_company_employees
  • Feed/messaging: get_feed, get_notifications, get_inbox, get_conversation, get_pending_invitations
  • Writes (gated): connect_with_person, send_message, create_post, react_to_post, comment_on_post
  • Session: whoami, health_check, close_session

Safety expectations

Automating LinkedIn can get an account restricted — there is no ban-proof tool. Default to a secondary account, respect the built-in daily caps, never disable pacing for real use, and stop immediately if health_check reports a checkpoint.

Contributing (code agents)

  • TypeScript, strict. npm run build (tsup), npm run typecheck, npm test (vitest), npm run lint (eslint) — all must pass; CI enforces them.
  • Voyager endpoints rotate. Write endpoint shapes are captured live via --writecapture (intercept the SPA's POST, abort it — zero side effects) and verified via --writeprobe; do not guess payloads.
  • Version is single-sourced from package.json (src/version.ts). Releases are automated on push to main when the version bumps (see .github/workflows).

Read the full file on GitHub · 49 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.

  1. 2d ago First seen · 49 lines · 582 tokens per session scan A 07abe4be1a9f

Subscribe to this mod's changes

linkedin-mcp AGENTS.md is an instructions file published in the GitHub repository devag7/linkedin-mcp (9 stars, last pushed 5d ago), licensed MIT. It adds 582 tokens to every session, about $0.0029 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 2026-08-31.

Related

Other instructions, from other repositories

qaskills AGENTS.md

Instructions for PramodDutta/qaskills, covering agents.md, project overview, common commands, run a single package and run tests in watch mode.

PramodDutta/qaskills · 2,851 tokens

agentic-playwright ai-native-workflow.instructions.md

Instructions for idavidov13/agentic-playwright, covering ai-native workflow, critical, main workflow (8 phases), phase 4 — confidence-gate format (mandatory) and proposal.

idavidov13/agentic-playwright · 2,744 tokens

agentic-playwright data-strategy.instructions.md

Instructions for idavidov13/agentic-playwright, covering data strategy, critical, file locations, instructions and phase 1: classify the value you need.

idavidov13/agentic-playwright · 2,684 tokens

agentic-playwright config.instructions.md

Instructions for idavidov13/agentic-playwright, covering configuration, critical, file locations, instructions and phase 1: understand how env files are loaded.

idavidov13/agentic-playwright · 2,424 tokens

agentic-playwright refactor-values.instructions.md

Instructions for idavidov13/agentic-playwright, covering refactoring enum values and static test data, critical, instructions, phase 1: find all consumers before touching anything and find all usages of the enum key.

idavidov13/agentic-playwright · 1,789 tokens

inspecto CLAUDE.md

Instructions for inspecto-dev/inspecto, covering inspecto — claude code development guide, project overview, monorepo structure, development phases (load each file as needed) and key architectural decisions.

inspecto-dev/inspecto · 1,014 tokens