A two-minute setup guide for the ContentIn MCP server. Create a key, paste one line into Claude Code, Claude Desktop or Cursor, and your assistant can write in your voice, pull your analytics, schedule and publish — without leaving the conversation.
The MCP server is part of the ContentIn Pro plan. Everything below assumes you have a Pro account.
Three things need to be in place. All of them live inside ContentIn.
The MCP server is part of the Pro plan. Every tool checks your plan live on each call, so an account that drops off Pro loses access straight away — no key rotation needed.
Publishing, scheduling and analytics all run through the LinkedIn account connected to that ContentIn profile. Connect it in ContentIn before you start, or the write tools have nowhere to publish and analytics will come back empty.
In ContentIn, open Settings → "Connect AI clients" and create a key. It starts with cimcp_ and is scoped to a single profile: the assistant you connect always works with that profile's voice, substance bank and calendar. You can hold up to five active keys per profile and revoke any of them at any time.
When you create an MCP key, ContentIn shows it a single time. Copy it straight into your client config or a password manager. Treat it like a password: anyone holding it can act on that profile. If you lose it or suspect it leaked, revoke it in settings and create a new one — revoking takes effect immediately.
One remote server, the same for every client. Replace YOUR_KEY with the key you just created.
One command in your terminal. Claude Code stores the server and picks it up on the next session.
claude mcp add contentin --transport http https://cms.contentin.io/mcp-server --header "X-MCP-Key: YOUR_KEY" Check it worked by running /mcp inside Claude Code — you should see contentin listed with its tools.
Edit the config file, add the entry below, then quit and reopen Claude Desktop.
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"contentin": {
"type": "http",
"url": "https://cms.contentin.io/mcp-server",
"headers": {
"X-MCP-Key": "YOUR_KEY"
}
}
}
} If the file doesn't exist yet, create it with exactly the content above. If it already has an mcpServers block, add the contentin entry alongside your existing servers rather than replacing it.
Same JSON, different file. Use ~/.cursor/mcp.json to make it available everywhere, or .cursor/mcp.json inside a project to scope it to that project. You can also add it through Cursor's settings under MCP.
{
"mcpServers": {
"contentin": {
"url": "https://cms.contentin.io/mcp-server",
"headers": {
"X-MCP-Key": "YOUR_KEY"
}
}
}
}Reload Cursor afterwards. The server shows up as contentin in the MCP panel once it connects.
ContentIn speaks the Model Context Protocol over Streamable HTTP. Point any compliant client at https://cms.contentin.io/mcp-server and send your key in the X-MCP-Key header. There's nothing to install — no local process, no bridge, no plugin per app.
Eight tools. Your assistant picks the right one from what you ask — you never call them by name.
list_postsDrafts, scheduled posts, published posts and saved ideas — filtered by status, date or a search term.
get_post_analyticsImpressions, members reached, reactions, comments, shares and engagement rate for a published post.
write_post_in_my_voiceBrain-dump the raw material and get back a draft built on the voice model trained on your own posts.
repurpose_postTake a post that landed and rework it from a fresh angle instead of repeating yourself.
generate_ideasPost ideas drawn from your topics, your audience and what has already resonated for you.
capture_substanceSave a story, an opinion or a number from any conversation into your substance bank, so future drafts inherit it.
schedule_postQueue a post for a specific time. Shows you the exact text and waits for your confirmation first.
publish_postPublish immediately. Shows you the exact text and waits for your confirmation — always.
Paste any of these into your client once the server is connected.
Both write tools are two-step by design. Your assistant calls the tool once and gets back the exact text plus a short-lived confirmation token; it has to show you that text and get your explicit go-ahead before the second call actually does anything. The token expires after five minutes, works once, and stops working if the post changed in between — so an assistant can't quietly queue something behind your back.
Each key is scoped to one ContentIn profile and carries no access to anything else on your account. Your LinkedIn password is never involved. Revoke a key from Settings at any time and it stops working immediately; create a fresh one whenever you need.
Each key has a daily ceiling on tool calls, which resets at 00:00 UTC. It's generous enough for normal work and exists to stop a runaway assistant from looping through your quota. If you hit it, the tools tell you so rather than failing silently.
The server re-reads your plan on each request rather than trusting a snapshot from when the key was created. That means access is always accurate — and if you upgrade, the tools start working without you doing anything.
The MCP server is included in the ContentIn Pro plan — nothing to buy separately. Start a trial, create your key, and your assistant is writing in your voice a couple of minutes later.
New to the Model Context Protocol? Read the LinkedIn MCP definition in our glossary, or try the free AI LinkedIn post generator first — no login required.