Connect LinkedIn to ChatGPT or Claude with MCP (2026)

To connect LinkedIn to ChatGPT or Claude, add Crispy's remote MCP endpoint, sign in with OAuth, and choose the tools you want available. Follow the Claude setup guide or ChatGPT setup guide because each client uses a different setup flow.

The catch is that LinkedIn is not like Gmail or Google Calendar. There is no open, personal API you can hand an OAuth token to. LinkedIn's official APIs (Marketing and Sales Navigator) are gated, partner-only, and cover almost none of the day-to-day actions an SDR or founder actually takes. So when someone asks 'how do I connect LinkedIn to ChatGPT,' the honest answer is: it depends entirely on which of three approaches you use, and they are not equal on safety, capability, or maintenance.

This guide walks through all three - copy-paste, browser scrapers, and a purpose-built MCP server - so you can pick the one that fits. We build the third, so we will be upfront about where the first two are genuinely fine and where they fall down.

Approach 1: copy and paste. This is where everyone starts, and for light work it is completely reasonable. You copy a profile, a message thread, or a job post into ChatGPT or Claude, and you ask for a draft. The assistant is excellent at the language part: rewriting a cold opener, summarizing a long thread, adapting tone. If your need is 'help me write better,' you do not need to connect anything at all - the chat window is the whole product.

Where copy-paste breaks down is volume and action. The assistant cannot see your inbox, cannot send anything, cannot check who accepted yesterday, and cannot run on a schedule. Every step is manual, and the context resets each time. It is a writing aid, not an operator. The moment you want the AI to actually take an action on LinkedIn, copy-paste is a dead end.

Approach 2: browser extensions and scrapers. The next rung is a tool that automates your logged-in LinkedIn session - a Chrome extension or a desktop app with an embedded browser that clicks around on your behalf. Some of these now bolt on an 'AI' layer. This works, and it can do real actions, but it comes with real costs. The automation fires from your own browser session, so it looks like traffic from your device and your browser has to stay open. Selectors break whenever LinkedIn ships a UI change. And crude, aggressive scraping is exactly what gets accounts restricted - LinkedIn is far better at detecting mechanical, browser-driven patterns than it was a few years ago. For an AI agent, this is also the wrong shape: the agent has no clean, stable set of actions to call, just a fragile screen it has to poke at.

Approach 3: a purpose-built MCP server. MCP, the Model Context Protocol, is an open standard for connecting AI assistants to external tools and data through a described interface. Instead of the model guessing at a web page, it sees typed actions such as sending a connection request, listing new messages, publishing a post, or running a search. Anthropic introduced MCP. Claude supports remote custom connectors, and ChatGPT supports custom MCP apps through Developer mode.

An MCP server for LinkedIn is a service that speaks this protocol and translates the agent's intent into LinkedIn actions. That is what Crispy is: a cloud LinkedIn MCP server with a documented tool catalog for AI agents. Your assistant connects once, then has a described toolset it can reason about and call.

Why MCP is the right abstraction. An agent is only as good as the tools it can call reliably. A stable, typed interface means the model can plan: 'first search for these people, then for anyone who accepted, send this follow-up, and flag replies that sound like buying signals.' Each of those is a discrete tool call with a predictable result, so the agent can chain them, handle failures, and explain what it did. A screen-scraper gives the model none of that - which is why agent-native tooling, not extensions, is where this is heading.

How to connect it to ChatGPT. ChatGPT supports custom MCP apps through Developer mode on the web. Full MCP tool support, including write actions, is currently available on Business, Enterprise, and Edu. Pro custom apps are limited to read and fetch actions. See OpenAI MCP app guidance for current availability. Add Crispy's remote endpoint at `https://crispy.sh/api/mcp`, choose OAuth, scan the tools, and approve the actions your workspace should expose. ChatGPT agent mode does not use custom apps.

How to connect it to Claude. Anthropic supports remote custom connectors on Claude and Claude Desktop for Free, Pro, Max, Team, and Enterprise plans. Free users can add one custom connector. See Anthropic custom connector documentation for current availability. Add Crispy's remote endpoint in Settings, then complete OAuth. Claude Code uses its own client-specific setup. Crispy exposes one endpoint, but each client owns its authentication and configuration flow.

Ready to configure a client? Follow the exact Claude setup guide or ChatGPT setup guide. For product evaluation, use the LinkedIn MCP server overview.

What the agent can actually do once connected. Crispy is not just outreach: the documented catalog includes tools for connection requests and messages, inbox triage, people and Sales Navigator searches, content publishing, post analytics, contacts, lists, and network analytics. The tool directory records the available tool pages. An agent can move across those areas in one workflow instead of only sending messages.

Before enabling write actions, review the client's approval controls and the limits documented for each tool. Crispy's safety calculator records configurable activity assumptions. The client still controls which tools it loads and when it asks for approval.

A connected agent needs memory about conversations and scheduled work. Crispy's Privacy Policy and Data Rights page describe the available access, export, retention, and deletion lifecycle for that managed data.

Building your own agent? Use the REST API. If you are not working inside ChatGPT or Claude but building a custom agent - in a framework, a workflow tool, or your own code - Crispy exposes the same capabilities over a REST API. Anything the MCP tools can do, your agent can do with a normal HTTP call, which means LangChain-style agents, internal automations, and no-code workflow builders all connect the same way.

A concrete example of what this unlocks: 'Every morning, check who accepted my connection requests, draft a short message referencing each person's most recent post, and put replies with a question into a list called Hot.' With copy-paste, each step is manual. With an MCP server, the client can compose documented tools subject to its approvals and the server's configured limits.

Getting started is deliberately direct. Create an account, connect LinkedIn in Crispy, and follow the exact guide for ChatGPT or Claude. ChatGPT uses OAuth for the custom app. Claude and Claude Code have distinct setup paths. From there, decide which tools and actions the client may use.

Ready to connect? Create your Crispy account, then follow the Claude setup guide or ChatGPT setup guide. Authentication uses OAuth. Do not paste an API key into the client.