Setup guide Connect LinkedIn to ChatGPT
Add Blabigo's MCP endpoint as a custom connector and ChatGPT can read your LinkedIn analytics and queue posts — using your own connected account, with no scraping and no browser automation.
Create a free accountThe only thing you need to paste
https://studio.blabigo.ai/api/mcp/linkedin Everything else is the client's standard OAuth flow. We lead with the URL rather than a screenshot tour because where connectors live in ChatGPT's settings, and which plans include them, has changed more than once — the endpoint has not.
The four steps
- 1
Create a Blabigo account and connect LinkedIn
Sign up free and connect your LinkedIn profile, plus any company Pages you manage, from the dashboard. You are authorizing Blabigo against your own account through LinkedIn's normal consent screen. ChatGPT never handles your LinkedIn credentials, because it never sees them.
- 2
Find the custom connector setting
In ChatGPT, open settings and look for connectors — the section for adding a remote MCP server of your own, as opposed to the pre-built integrations. Exactly where this sits, and which plans include it, has changed across releases, so trust the current interface over any screenshot you find online, including ours.
- 3
Add the Blabigo endpoint
Paste the MCP endpoint URL. ChatGPT performs OAuth discovery against it, opens a browser flow, and you approve the connection under your own Blabigo account. Nothing permanent is copied between the two applications — the client receives a scoped token it can hold and you can revoke.
- 4
Confirm it works
Ask ChatGPT to list your connected LinkedIn accounts. Getting your profile and Pages back proves authentication, scope resolution and the LinkedIn API call all work — which is more than a green checkmark in a settings screen tells you.
If your plan has no custom connectors
This is the common sticking point, and it is not something we can fix from our side. Three ways round it:
Use a client that does support it
Claude Desktop and Claude Code both connect from the same URL, and the account, the data and the limits are identical — only the client differs. If you are blocked purely on connector support, this is the fastest route.
Drive it from your own code
The same capabilities are available as an authenticated HTTP API. If what you actually want is ChatGPT's model rather than its connector UI, call the model from your own code and give it Blabigo's API as a tool.
Use the CLI for the scripted parts
Reporting, release notes and anything that runs on a schedule do not need a conversation at all. The Blabigo CLI covers those from a shell or CI job.
What ChatGPT can and cannot do once connected
It can list your accounts, read post and account analytics, refresh metrics, list and read posts, create and edit drafts, queue them, reschedule, cancel and archive. It cannot publish immediately and it cannot delete anything — those tools do not exist, for any client.
The full guardrails →Using a different assistant?
Same endpoint, same account, same limits — only the client differs.
Connect to Claude
A two-minute setup walkthrough for Claude Desktop, Claude Code and any config-file client — plus what to do when the connection fails.
Setup guide →
Connect to Gemini
One command in Gemini CLI, automatic OAuth discovery, and the settings.json form for anyone who prefers to edit it by hand.
Setup guide →Frequently asked questions
- Can ChatGPT post to LinkedIn?
- Through Blabigo's MCP server, ChatGPT can draft a post and place it on your publishing queue for a future time. It cannot publish to LinkedIn directly — Blabigo's scheduler does that at the scheduled time, and no tool in the integration reaches LinkedIn on demand. So the accurate answer is that ChatGPT can write and queue, while you keep the last look.
- How do I connect LinkedIn to ChatGPT?
- Create a Blabigo account, connect your LinkedIn profile to it, then add Blabigo's MCP endpoint as a custom connector in ChatGPT and approve the OAuth flow in your browser. The only thing you paste is the endpoint URL. Custom connector support depends on your ChatGPT plan and the current release.
- Does ChatGPT support MCP servers?
- ChatGPT has supported connecting to remote MCP servers, though the feature's name, its location in settings and the plans that include it have changed across releases. If your settings offer custom connectors, Blabigo's endpoint works like any other remote MCP server. If they do not, use an MCP client that does, or call Blabigo's HTTP API from your own code.
- Is this different from a ChatGPT LinkedIn plugin?
- Yes. Plugins were an earlier and now-retired mechanism. MCP is an open protocol that is not specific to any one assistant, which is the practical advantage here: the same Blabigo endpoint serves ChatGPT, Claude and anything else that implements the protocol, so you are not re-integrating every time you change assistant.
- Is it safe to connect LinkedIn to ChatGPT?
- The risk is bounded by what the integration permits rather than by the assistant. Through Blabigo, no agent can publish immediately, none can delete a post, and server-side quotas cap what any credential can queue. You approve a scoped token during setup and can revoke it from the Blabigo dashboard at any time, which stops access regardless of what still holds the token.
- Does this scrape LinkedIn?
- No. Everything goes through your own connected LinkedIn account and the official API, using the permissions you granted. Nothing automates the LinkedIn website in a browser and nothing logs in as you.
More on AI and LinkedIn
AI & Agents
The hub for everything Blabigo publishes about AI agents, the Model Context Protocol, and automating LinkedIn without handing over your feed.
Read more →LinkedIn MCP server
The endpoint, all 13 tools, the three OAuth scopes, and the two ways to authenticate. Start here if you want the technical picture.
Read more →Connect to Claude
A two-minute setup walkthrough for Claude Desktop, Claude Code and any config-file client — plus what to do when the connection fails.
Read more →Scheduling with AI
The draft → review → queue loop, the prompts that make it work, and why an agent that queues beats an agent that publishes.
Read more →Analytics for agents
Read-only access to impressions, clicks and engagement, so you can ask your assistant what actually worked instead of exporting spreadsheets.
Read more →Agent guardrails
The written safety contract: no instant publish, no delete tool, hard server-side quotas, and an audit trail per credential.
Read more →LinkedIn API alternative
Why LinkedIn's own API is hard to get, what you can and cannot do without partner access, and how to ship without waiting on an approval queue.
Read more →MCP vs Zapier & n8n
Where trigger-action automation is the right tool, where a conversational agent is, and why the answer is usually both.
Read more →Connect to Gemini
One command in Gemini CLI, automatic OAuth discovery, and the settings.json form for anyone who prefers to edit it by hand.
Read more →Claude Code & CLI
For developers: the MCP transport, the CLI, exit codes, idempotency keys, and shipping release notes from CI.
Read more →One endpoint, any assistant
MCP is an open protocol, so you are not re-integrating when you switch.
Start freeBlabigo is an independent product, not affiliated with, authorized by, endorsed by or sponsored by LinkedIn Corporation, Microsoft or OpenAI. “LinkedIn” and “ChatGPT” are trademarks of their respective owners, used here descriptively to identify the services this software works with. ChatGPT's connector support and plan availability are OpenAI's to change.