Post to LinkedIn from Claude or ChatGPT with an MCP server

Is there an official LinkedIn MCP server?

No. LinkedIn and Microsoft publish no MCP server for posting. ChatGPT’s app directory has LinkedIn apps for looking people up and for LinkedIn Ads, and neither posts. What people install instead falls into three groups: servers that drive your logged-in LinkedIn session to read profiles, jobs and your inbox; outreach services; and a few small servers that post through LinkedIn’s official API with a developer app you register yourself.

Read on 1 October 2026 from each project’s own page. Descriptions of other servers are their own claims; Mellow has not tested them.

Tools that drive your session act as you inside LinkedIn’s website. LinkedIn’s User Agreement forbids automated access of that kind, and it can get an account restricted. Posting through the API is the route LinkedIn provides: Share on LinkedIn for members, and the vetted Community Management API for company pages.

What LinkedIn account do I need?

A LinkedIn personal profile, or a company page on which you are an admin. When you connect, Hub asks which one to post as. Each connection is one channel, so a profile and a page you run are two channels, and one post can go to both. Hub publishes; it does not read your feed, search jobs or send messages.

1. Open Accounts in Hub and choose LinkedIn, or ask the assistant to call connect_channel with platform set to linkedin. That tool only returns a link and an instruction for a person. It needs the channels:connect permission.
2. Open the link and sign in to LinkedIn yourself. Hub never sees your LinkedIn password.
3. Tell the assistant you are done. It calls list_channels with refresh: true and uses the returned channel ID, which begins with spc_. A username is not a substitute for that ID.

Connect Claude, ChatGPT, Cursor or another MCP client

Every client uses the same server URL, https://www.mellow.world/mcp, over Streamable HTTP. A client signs in with OAuth 2.1 (dynamic client registration and PKCE) or sends an owner-created Hub API key as a Bearer token. Menus change between client versions, so the official guides linked below describe the current screens. The last column says only what Mellow itself has tested, on any network.

1. Add the server in your client and select Connect. Sign in to Mellow if asked. Hub’s consent screen names the app that is asking.
2. Choose the permissions the task needs (below), select your LinkedIn channel, choose review or autopilot, a daily ceiling and an expiry, then approve.
3. Back in the client, run the read-only check from the prompts below. Confirm the profile, the mode and the LinkedIn channel ID. Agents shows the grant’s permissions, channels and expiry.
4. If a client cannot complete OAuth, create a key in Agents and set it as the client’s Authorization: Bearer header, from its secret settings or an environment variable. Never paste a key into a chat.

Which permissions to approve

The consent screen arrives with every permission the assistant asked for already ticked, except spending AI credits. Untick anything it should not have.

What you delegate, and how to take it back

Hub treats an assistant’s access as a delegation you give once, with limits: the permissions, the channels (the ones you select, or explicitly all), review or autopilot, a daily ceiling of 1 to 1,000 posts (50 by default) and an expiry of 1, 7 or 30 days (30 by default). Autopilot is the default: the assistant publishes on its own within those limits. Choose review and each post waits for you to approve it in Hub. A key or a connected app cannot approve its own post.

Hub records the posts an assistant creates or has refused, approvals, reschedules, cancellations and connection attempts in a journal you read in Agents. Revoking a key or a connected app takes effect on its next request. Publishing always needs an idempotency key, so a retried request cannot publish twice.

LinkedIn rules Hub checks before anything is sent

This table is generated from the registry that validate_post enforces, the same one behind the rules for every network. These are Hub’s input rules; LinkedIn still judges the media itself when it fetches it.

LinkedIn publishes nothing without text, so an image or a video alone is refused before it is sent. Posting the same words to X or Threads? Their limits are far shorter than LinkedIn’s 3,000: give those channels their own caption in perChannel rather than cutting the LinkedIn version. LinkedIn keeps line breaks; styled letters from a text formatter are allowed but count double in Hub’s check.

LinkedIn’s own help gives the same 3,000-character limit for a post (LinkedIn Help, read on 1 October 2026).

When validate_post refuses the post

Read ok, issues and notes in the result. The check publishes nothing and reports every problem at once, each with its field and, for a network rule, its channel. Fix them together and validate again.

Other refusals concern the request or the grant: schedule_in_past (use a future time with a UTC offset), insufficient_scope (approve a delegation with the missing permission), channel_out_of_scope (the channel is not in the grant), and at creation daily_limit_reached and idempotency_key_reused. A passing check is not proof of publication: LinkedIn can still refuse the media or the account. The free post checker runs the same input rules on a draft before you connect anything.

Prompts you can paste

Replace the bracketed parts. Each prompt names the tools to call, so the assistant does not have to guess the order.

Use only Mellow Hub. Call whoami, then list_channels, then list_platforms.
Tell me my LinkedIn channel ID, whether it is my profile or a company page,
whether this connection is in review or autopilot mode, how many posts it
may still create today, and LinkedIn's rules. Do not create anything.

Use Mellow Hub. Validate this as a text post for my LinkedIn channel:
[your post]

Keep my line breaks. If validate_post reports an issue, fix it and show me
the new version before continuing. Then schedule it for 08:30 on [date] in
[your timezone], with scheduledAt written with an explicit UTC offset.
Call create_post once with idempotencyKey "linkedin-[date]-0830", then
get_post, and tell me the LinkedIn target's status.

Use Mellow Hub. Post the images at [public https URLs, in order] as one
post to my LinkedIn and Instagram channels.
LinkedIn caption: [longer, with line breaks]
Instagram caption: [shorter, with up to 5 hashtags]

Call register_media on each image. Put each caption in perChannel under
its channel ID. Call validate_post and fix every issue. Then call
create_post once with idempotencyKey "carousel-[short-name]-1" and call
get_post. Report each target's status and link separately.

Media has to be reachable at a public https URL when LinkedIn fetches it. An agent that can make HTTP requests, such as Claude Code or a script of your own, can instead call request_upload_url, send a local file with PUT to the returned uploadUrl and use the returned mediaUrl. An assistant that only has Hub’s tools cannot send file bytes itself.

Publish once, then read the LinkedIn result

create_post is the step that publishes or schedules. It needs an idempotencyKey of 8 to 120 letters, digits or the characters . _ : -, stable for this post. If the response is lost or times out, send the same request with the same key: Hub returns the original post instead of making a second one. Reusing a key for different content is refused.

Under a review-mode grant the post comes back as pending_review and waits until you approve it, signed in, in Hub. Under autopilot it goes out at scheduledAt, or immediately without it. Always write scheduledAt with Z or an explicit UTC offset.

Then call get_post and read the LinkedIn entry in targets, not only the post’s status. publishing means LinkedIn has not reported a result yet; published comes with the post’s link; failed comes with the network’s message. In a post to several networks each target settles on its own and the post can end partial: republish only the failed channel, with a new key. Once LinkedIn has published a post, Hub cannot edit or delete it; cancel_post works only before it goes out.

Each destination counts once against your plan: one post to LinkedIn and two other networks is three publications. Validating, drafting and connecting work without a plan; publishing needs an active one. See plans.

What Mellow has tested with LinkedIn

Production records on 1 October 2026 show six LinkedIn publications through Hub between September 5 and October 1, each reaching published with a public link, all on one personal profile. Two came through Hub’s MCP endpoint from a Claude Code session using an owner-created key: on September 29 a video posted to LinkedIn together with Instagram, Facebook, Threads, X and TikTok, and on September 30 a post created the evening before went out at the time set for it, after Claude’s claude.ai connector had moved that time. On October 1 a post created with an owner-created key on September 30 at 15:59 UTC for 12:30 UTC went out at 12:31 UTC, together with Facebook, Instagram, Pinterest, Threads and X, with nothing changed in between. Publication was confirmed from each network’s result and public link, not from a screenshot.

Not tested yet: a LinkedIn company page, a carousel of images on LinkedIn, and connecting through ChatGPT or Cursor.

Questions

Related

• LinkedIn text formatter: bold, italic and lists, with a preview of the fold.
• Threads MCP guide and X MCP guide for the shorter networks you might post the same words to.
• Publish to social media with an MCP server: the workflow for every network.
• Before an AI agent posts: an MCP checklist.
• API and MCP reference and rules for every network.
• Plans: each destination counts once against the monthly publications.