MCP + LinkedIn: how AI agents automate outreach

Model Context Protocol (MCP) is an open standard that lets AI agents use external tools. Think of it as USB-C for AI — a universal connector that works across models and platforms. Claude, ChatGPT, and dozens of other AI tools already support it.

Crispy exposes 43 LinkedIn tools via MCP. Each tool maps to a specific LinkedIn action: searching for people, viewing profiles, sending connection requests, writing messages, creating posts, and more. When an AI agent connects to Crispy, it discovers these tools automatically and can use them conversationally.

Here's a real workflow: you tell Claude 'Find 10 marketing directors at Series B startups in Berlin and send each a personalized connection request.' Claude calls search_people to find matches, get_profile to read each person's background, and send_invitation with a custom note referencing their specific work. The entire sequence runs in under a minute.

What makes this different from traditional automation tools? Three things. First, the AI agent decides the strategy — you describe the goal, it figures out the steps. Second, personalization is genuine — the agent reads each profile and writes unique messages. Third, everything stays within LinkedIn's safety limits — Crispy enforces per-category daily caps (15 invitations, 150 messages, etc.) to protect your account.

For sales teams, this means outbound that actually scales. One person with an AI agent can do the research and personalization work of an entire SDR team. And because Crispy is stateless, there's no data lock-in — switch AI tools anytime and your LinkedIn data stays on LinkedIn.

We're seeing teams run entire outbound campaigns, content strategies, and network-building operations through MCP. The common thread: they describe what they want in natural language, and the AI agent handles the execution using Crispy as its LinkedIn toolkit.