Hermoso is a marketing MCP server: 301 tools over one OAuth’d endpoint that let an agent research the ads already running in a market, generate finished image and video ads, publish them, and build the paid campaigns behind them. Claude Code reaches all of it through one connection. This page is about one slice of that — what Claude Code can actually do on LinkedIn, and what LinkedIn will not let it do.
Connect Hermoso to Claude Code
- Create an API key. In Hermoso, open Settings → Agents & API keys and press ＋ Create API key. It looks like
hmk_…and carries real spend authority, so treat it like a password. - Add the server.
claude mcp add --transport http hermoso https://app.hermoso.ai/mcp \ --header "Authorization: Bearer <your key>" - Or run it over stdio if you would rather not hold an HTTP config:
claude mcp add hermoso -e HERMOSO_TOKEN=hmk_… -- npx -y hermoso mcp - Ask Claude Code for something. “Pull my three closest competitors’ longest-running ads and remix the best hook into a 9:16 video,” or “post this render to the channel.” The agent picks the tools; you approve the spend.
Both forms reach the same 301 tools. The HTTP form is the hosted server; the stdio form runs the published hermoso npm package locally and talks to the same account.
Then connect LinkedIn itself, once, under Settings → Connectors in Hermoso. That is an OAuth consent screen, so it is the one step that needs a browser — everything after it is a tool call.
The LinkedIn tools Claude Code gets
post_to_linkedin_page— publishes to a company Page — text, an image, a video, or a multi-image post — with alt text.post_to_linkedin— publishes to a personal profile, which stays switched off until you explicitly share that identity.list_linkedin_pages— the Pages you have shared with this brand, with their organization ids.schedule_post— queues it, carryinglinkedinOrganizationIdso the right identity posts.manage_linkedin_post— edit the copy of a post, or delete it.linkedin_page_analytics— organic Page performance — follower gains, Page views, and post impressions, clicks and engagement, per Page or per post.search_linkedin_ads— the LinkedIn Ad Library — the one public ad library that exposes real impression counts.
LinkedIn is the channel where identity is a permission rather than a preference. One person usually administers several companies’ Pages, so Hermoso makes the postable identities an explicit choice: only the Pages you have ticked under Manage accounts can be posted to, an unticked Page is refused server-side rather than in the UI alone, and the personal profile is off unless you turn it on. An agent that asks which Page rather than assuming is doing the right thing.
LinkedIn limits worth knowing before you automate anything
| Text | A LinkedIn post is capped at 3,000 characters. It is enforced when the post is created or queued — refused while you are still there to fix it, rather than silently cut on the way out. |
|---|---|
| Visibility | Public only — “a LinkedIn post publishes to the profile or company Page — LinkedIn has no unlisted, private or draft post.” |
| Carousel | 2 to 20 images, from a company Page. Both bounds are LinkedIn’s own: “A MultiImage post is a post containing multiple images (minimum of 2 images and maximum of 20 images)”, and the schema adds “Only supports images”. Two refusals follow from that and both are by name rather than by silent downgrade: a video slide is refused because LinkedIn’s multi-image post cannot carry one, and a personal-profile carousel is refused with the way forward — “Pass linkedinOrganizationId (list_linkedin_pages) — a personal-profile carousel is not something Hermoso can publish.” |
| Which account | linkedinOrganizationId. Unset means the member’s own profile, never “probably the company” — so the field is how you say which Page, and leaving it out is a decision rather than an accident. |
Try it in Claude Code
Ask for it in ordinary language — these are sentences, not a DSL:
“Resolve the company Page id, publish the post in ./drafts/case-study.md to it with the six images in ./assets, and append the URL to CHANGELOG.md.”
That walks list_linkedin_pages → plan_ad → render_ad → post_to_linkedin_page → linkedin_page_analytics. Claude Code asks before it runs a tool, and the transcript is right there in the terminal — so a publish step is a line you can read before you press y.
Claude Code on LinkedIn: the part that bites
Always start with list_linkedin_pages in a script — the organization id is what selects the Page, and an unset id means the member’s personal profile rather than “probably the company”. That default is deliberate and it is why the personal profile stays off until explicitly shared. A carousel needs the Page id for a second reason: multi-image posts are a company-Page feature.
A 301-tool manifest is not free in context. For long unattended runs the hermoso CLI is the cheaper path: the agent shells out per command instead of carrying the whole manifest.
Research LinkedIn before you post
search_linkedin_ads reads the LinkedIn Ad Library, which is unusual among public ad libraries in exposing real impression counts — so B2B competitor research on LinkedIn can be ranked by actual delivery rather than by guesswork about what is running.
The paid half
create_linkedin_ads_campaign_group → create_linkedin_ads_campaign → create_linkedin_ads_creative builds the tree, and everything is born as a draft. set_linkedin_ads_status is the only switch that arms real money and it refuses without an explicit confirmation. One access note that is better said than discovered: LinkedIn meters ad writes by the API tier your own ad account holds — reporting and reads are unrestricted, and on the development tier an app may edit a small number of ad accounts, each registered by hand.
What Claude Code cannot do on its own
An agent with a budget is only useful if the blast radius is bounded, so the fence is in the server rather than in a prompt. Every ad campaign, ad set, ad group and ad is created paused, and the status switches that arm real money refuse to run without an explicit confirmation flag. Every render is quoted first — hermoso_capabilities publishes each model’s exact credit cost before anything spends — and credits are reserved before the first provider call and settled at the exact cost afterwards, so a failed dispatch refunds rather than leaving you billed for nothing. Deletes are confirm-gated too, and every campaign tree is read back from the ad platform before your agent tells you what it built.
One step is deliberately not headless: linking an account is an OAuth consent screen, so you connect the channel once in a browser. Everything after that is a tool call.
The rest of the matrix
From Claude Code, post to: Facebook · Instagram · Threads · TikTok · YouTube · X · Pinterest — or see everything Claude Code can publish to.
Post to LinkedIn from: Claude · ChatGPT · Cursor · Codex · Cline · OpenClaw · Hermes · Claude Code marketing
Frequently asked questions
Can Claude Code post to LinkedIn?
Yes, through Hermoso's MCP server. Create an API key in Hermoso under Settings → Agents & API keys, then add https://app.hermoso.ai/mcp to Claude Code with an Authorization: Bearer header. Claude Code then has 301 tools, including the ones that publish to LinkedIn — and the ones that research the ads already running in your market and render the creative in the first place.
How do I connect LinkedIn to Claude Code?
Two steps, once each. Create an API key in Hermoso under Settings → Agents & API keys, then add https://app.hermoso.ai/mcp to Claude Code with an Authorization: Bearer header. Then connect LinkedIn inside Hermoso under Settings → Connectors, which is an OAuth consent screen in a browser. After that Claude Code publishes to LinkedIn as an ordinary tool call.
What is the LinkedIn caption limit when posting from Claude Code?
A LinkedIn post is capped at 3,000 characters. Hermoso enforces it when the post is created or queued, so Claude Code is told immediately rather than failing later when nobody is watching.
What does it cost to post to LinkedIn from Claude Code?
Publishing to LinkedIn costs no credits; LinkedIn charges nothing per API call. Credits are spent on the render. Plans are $19, $49 and $149 a month for 1,000, 3,000 and 10,000 credits, and every feature is on every plan including Free — the only exception is enterprise SSO.
Start free — 25 credits at signup and 250+ more to earn, and every feature on every plan.
Start free → See pricing