{
  "markdown": "# linkedin-mcp\n\n[![Apex MCP — featured on mcpexplorer.com](https://mcpexplorer.com/badge/apex.svg)](https://mcpexplorer.com/mcps/apex)\n\n**Governed LinkedIn hands for AI agents.** This is the public face of [Apex by LeadShark](https://www.apex.new) — an MCP loadout that lets Claude, ChatGPT, or Cursor operate a real LinkedIn account in plain English: find buyers, rank intent, comment, connect, and message. Every action is paced, capped, approval-queued where needed, and fully logged.\n\nThis repo contains the **discovery endpoint** — a minimal, dependency-free MCP server, served live at:\n\n- **`https://www.apex.new/mcp`** (alias: `https://www.apex.new/linkedin-mcp`)\n\nMount it in any MCP host and it completes the handshake instantly — no account, no auth — then briefs your agent on what the full loadout is and how to get it.\n\n## The mission\n\nMost LinkedIn tooling automates what you already decided: schedule this post, DM whoever comments. Apex is the layer above that — the **intelligence that decides what to automate and where to show up**. The activation path is intelligence-first, not automation-first. In five words:\n\n> **Discover demand. Engage with context.**\n\nAn agent running Apex works a loop: **See → Decide → Act.** Find the posts and people where attention already is, figure out who's worth engaging and with what angle, then engage — inside the account's safety budget.\n\n## The loadout — 40 tools, See → Decide → Act\n\nThe full authenticated server at `https://apex.leadshark.io/mcp` equips your agent with:\n\n### See / discover — where is the demand? (Apex, except `discover_lead_magnets`)\n`search` · `discover_lead_magnets` · `list_signals` · `feed` · `list_recent_posts` · `list_person_posts` · `list_post_engagers` · `get_person_activity`\n\nFind people and companies, pull a continuously refreshed radar of prospect-rich lead-magnet posts, list your heat-scored inbound signals, turn one viral post into a warm lead list, and see the rooms a prospect is already in (`get_person_activity` — who they comment on, what they react to). `discover_lead_magnets` is available on the **Pro+** MCP floor (it doubles as content market-signal); the rest of this group is Apex.\n\n### Decide / context — who is worth your time?\n`enrich` · `enrich_company` · `get_lead_activity`\n\nStructured profiles for a person or account: role, company, activity, connections. The agent ranks ICP fit and intent and picks the angle — comment, connect, or ignore. Built on `enrich`, the most-used signal in the loadout.\n\n### Act — engagement\n`comment_on_post` · `react_to_post` · `send_connection_request` · `engage_with_comment` · `manage_invitations`\n\nShow up where the prospect's attention already is — warm them up in public before anything lands in their inbox. Triage inbound connection requests too.\n\n### Act — messaging\n`list_recent_messages` · `get_messages_with_person` · `send_message` · `send_email`\n\nRead the inbox, pull a full thread with one person, send the DM — deduped, paced, and logged. `send_email` sends through your own connected Resend account (BYO key).\n\n### Company Pages\n`list_companies` (Pro+) · `comment_as_company` · `react_as_company` · `manage_company_reply_automations`\n\nList and schedule to pages you administer on **Pro+**; acting in the page's *voice* — commenting, reacting, and running reply-only comment automations as the page — is **Apex**.\n\n### Pages & captured leads (Apex)\n`list_lead_pages` · `get_page_leads` · `list_lead_magnet_links`\n\nRead the leads your lead magnets captured — pages with capture stats, the deduped enriched email leads for a page, and your standalone `leads.sh` capture links — to feed the enrich → act loop.\n\n### Automations & scheduled posts (Pro+ baseline)\n`create_automation` · `list_automations` · `get_automation` · `edit_automation` · `suggest_automation_settings` · `schedule_post_with_automation` · `list_scheduled_posts` · `get_scheduled_post` · `edit_scheduled_post` · `cancel_scheduled_post`\n\nThe execution layer: comment→DM lead-magnet automations and pre-automated post scheduling. Apex decides *what* to run; these run it.\n\n### Safety, limits & history\n`manage_activity_limits` · `set_daily_dm_limit` · `list_actions`\n\nCheck budgets before acting, adjust caps, and read the audit trail — what the agent already did, what's staged for approval, why something was refused, and the current safety mode.\n\nFull per-tool reference (parameters, access, tiers): **[apex.new/tools.md](https://www.apex.new/tools.md)**\n\n## The safety model (this is the point)\n\nEvery write the agent makes shares the **same daily/weekly budgets** as the account's automations (DMs, replies, connections), honors the **do-not-engage list**, and is **paced and rate-limit-aware**. Actions can be refused or queued for the user's approval — and the agent is told why. Limits are calibrated from LeadShark's production LinkedIn volume, not guesswork. Agents are expected to check `list_actions` before acting and to work within limits rather than around them.\n\n## What this repo's server does\n\nThis discovery stub speaks MCP over **Streamable HTTP** (JSON-RPC 2.0 over POST, JSON responses, stateless, no SSE) and exposes three no-auth informational tools:\n\n| Tool | What it returns |\n| --- | --- |\n| `about_apex` | What Apex is, tier pricing, trial paths, key links |\n| `get_setup_steps` | The 5-step connect flow (account → LinkedIn → 24h unlock → mount MCP → first play) |\n| `first_plays` | Copy-paste starter prompts: verify, discover, enrich, act |\n\nIt has **no LinkedIn powers of its own** — it's the handshake and the briefing, not the hands.\n\n## Try it\n\nAdd `https://www.apex.new/mcp` as a custom connector / MCP server in your AI app, or run this repo locally:\n\n```bash\nnode server.mjs          # Node 18+, zero dependencies, listens on PORT (default 3000)\n```\n\nHandshake by hand:\n\n```bash\ncurl -s -X POST http://localhost:3000/mcp \\\n  -H 'Content-Type: application/json' \\\n  -d '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"initialize\",\"params\":{\"protocolVersion\":\"2025-06-18\",\"capabilities\":{},\"clientInfo\":{\"name\":\"curl\",\"version\":\"0\"}}}'\n```\n\n## Get the full loadout\n\n1. Create a [LeadShark account](https://apex.leadshark.io/auth/register) — free 7-day trial, no card.\n2. Connect the LinkedIn account the agent will operate.\n3. Unlock the one-time **24-hour Apex operator window** (Settings → Apex Settings).\n4. Add `https://apex.leadshark.io/mcp` to your AI app and authorize with LeadShark.\n5. Ask: *\"Check if you can see LeadShark Apex and list the tools available.\"*\n\nApex is **$119/mo** after the trial. LeadShark Pro ($39/mo) automates your lead magnet; Pro+ ($59/mo) scales automations and gated funnels; Apex is the operator loadout on top.\n\n- Website: [apex.new](https://www.apex.new) · Pricing: [apex.new/pricing](https://www.apex.new/pricing)\n- MCP setup guide: [apex.leadshark.io/docs/mcp](https://apex.leadshark.io/docs/mcp)\n- Agent operating guide: [apex.new/agents.md](https://www.apex.new/agents.md)\n- Machine-readable index: [apex.new/llms.txt](https://www.apex.new/llms.txt)\n\n## License\n\nMIT\n",
  "bytes": 7059,
  "sha": "c66f2700f7d94e0df55645d57a450efcc26c99d21cde6f405608991a85f4d9c6",
  "repo_slug": "rzere/linkedin-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_rzere_linkedin_mcp_dd9ba44a/readme"
}