Show HN: An MCP server that lets Claude or ChatGPT schedule LinkedIn posts ContentIn released an MCP server at https://mcp.contentin.io/mcp-server that lets Claude, ChatGPT and Claude Code schedule and publish LinkedIn posts from inside a conversation, with setup requiring only pasting one URL and signing in via OAuth rather than copying an API key. A free ContentIn for Agents account allows 2 posts a day and 30 a month per LinkedIn profile, up to 14 days ahead, with images; the Agent plan costs $29 a month or $276 a year per profile with a 7-day trial, and Agent Pro costs $49 a month or $468 a year. The server is included for existing ContentIn Growth and Pro subscribers, and ChatGPT requires developer mode enabled under Apps to add the custom connector. A two-minute setup guide for the ContentIn MCP server. Paste one URL into Claude, ChatGPT, Claude Code or another AI app and sign in with ContentIn. Your assistant can then schedule and publish to LinkedIn without leaving the conversation. No key to copy. Free, no card: with a free ContentIn for Agents https://contentin.io/linkedin-for-ai-agents/ account your AI can schedule and publish to LinkedIn, 2 posts a day and 30 a month per profile, up to 14 days ahead. It can attach images, read a voice summary and see how many people each post reached. Analytics, your full voice profile, past posts, saved material and ContentIn's writing and idea tools need the Agent plan $29 a month or $276 a year per LinkedIn profile, 7-day trial . Agent Pro $49 a month or $468 a year adds the people who engaged and your comments. Already on ContentIn Growth or Pro? The MCP server is included in your plan https://contentin.io/linkedin-mcp-server/ , so use your existing account. Everything below works for both. Two things need to be in place. Both live inside ContentIn. Create a free ContentIn for Agents account https://app.contentin.io/signup?product=agent&ref=setup guide and add your LinkedIn profile URL. Free covers posting: your AI can schedule and publish 2 posts a day and 30 a month per LinkedIn profile, up to 14 days ahead, with images. A plan adds analytics, your full voice profile, past posts, saved material and ContentIn's writing and idea tools. Which tool needs which plan troubleshooting is under troubleshooting. Already on ContentIn Growth or Pro? Use your existing account; the MCP server is included. Publishing and reach numbers run through the LinkedIn account connected to the ContentIn profile you pick. On ContentIn for Agents, connect it on the ContentIn for Agents page https://app.contentin.io/agents under Connect LinkedIn for publishing . Do this before you connect your AI app, so your first request can already publish. On Growth or Pro, connect it in the web app under Profiles → Connections. Until it's connected, your AI has nowhere to publish. One remote server, the same URL for every client. There's no key to copy and no header to set: you paste the URL, sign in with ContentIn, and you're connected. In Claude.ai, open Customize → Connectors → Add → Add custom connector , paste the URL below and click Continue . Claude then shows sign-in and OAuth client options. Keep what is already selected and click Add . Then click Connect , sign in with ContentIn, pick your profile and approve ContentIn. https://mcp.contentin.io/mcp-server Copy it exactly. The path is /mcp-server , not /mcp , and there's nothing to add after it. Added the connector earlier with a key in the URL? It keeps working until you remove it and reconnect with the plain URL above. Same as Claude.ai: open Customize → Connectors → Add → Add custom connector , paste https://mcp.contentin.io/mcp-server and click Continue . Claude then shows sign-in and OAuth client options. Keep what is already selected and click Add . Then click Connect and approve ContentIn. A connector you add on Claude.ai shows up in Claude Desktop too, so if you've done it once, you're done. No config file to edit. Add the server with one command in your terminal: claude mcp add --transport http contentin https://mcp.contentin.io/mcp-server Then start Claude Code, run /mcp , select contentin and choose Authenticate . Your browser opens the ContentIn sign-in page; approve, and contentin shows as connected with its tools. Until the ContentIn app is approved in ChatGPT, ChatGPT needs developer mode for custom connectors. Turn on developer mode in ChatGPT's settings under Apps , then create a new app or connector, paste https://mcp.contentin.io/mcp-server as the server URL and choose OAuth as the authentication. ChatGPT sends you to the ContentIn sign-in page; approve, and the tools are available in your chats. Add the entry below to ~/.cursor/mcp.json to make it available everywhere, or to .cursor/mcp.json inside a project to scope it to that project. Just the URL, no headers. { "mcpServers": { "contentin": { "url": "https://mcp.contentin.io/mcp-server" } } } Open Cursor's MCP settings: the contentin server asks you to sign in. Click it, approve on the ContentIn page, and the server shows as connected. Add the server to .vscode/mcp.json in your workspace or run MCP: Add Server from the command palette and paste the URL : { "servers": { "contentin": { "type": "http", "url": "https://mcp.contentin.io/mcp-server" } } } Start the server when VS Code offers to. It asks to sign in with ContentIn; approve, and the tools are available to Copilot's agent mode. ContentIn speaks the Model Context Protocol over Streamable HTTP, with standard MCP OAuth sign-in. Point any compliant client at https://mcp.contentin.io/mcp-server and it discovers the ContentIn sign-in on its own. There's nothing to install: no local process, no bridge, no plugin per app. If the client can't open a browser, use an API key api-keys instead. Scripts, CLIs and headless agents that can't open a browser to sign in can use an API key instead. The key goes in the X-MCP-Key header on every request. Steps for n8n, OpenClaw and Gemini CLI follow below. Where you create one depends on your account: A key starts with cimcp and is scoped to a single profile. You can hold up to five active keys per profile and revoke any of them at any time. Claude Code with a key: claude mcp add --transport http contentin https://mcp.contentin.io/mcp-server --header "X-MCP-Key: YOUR KEY" Any client that takes a JSON config with headers: { "mcpServers": { "contentin": { "type": "http", "url": "https://mcp.contentin.io/mcp-server", "headers": { "X-MCP-Key": "YOUR KEY" } } } } Add an MCP Client node and set the transport to HTTP Streamable . Use https://mcp.contentin.io/mcp-server as the endpoint. For authentication, add a Header Auth credential with the name X-MCP-Key and your key as the value. The tools then show up for your workflow or AI Agent node. Merge this into the mcp block of ~/.openclaw/openclaw.json and put your key in place of YOUR KEY . Don't set auth: "oauth" on the same entry, because OpenClaw ignores the header while OAuth is on. { mcp: { servers: { contentin: { url: "https://mcp.contentin.io/mcp-server", transport: "streamable-http", headers: { "X-MCP-Key": "YOUR KEY" }, }, }, }, } Add the server to the mcpServers block of ~/.gemini/settings.json with your key in the header, then restart Gemini CLI: { "mcpServers": { "contentin": { "httpUrl": "https://mcp.contentin.io/mcp-server", "headers": { "X-MCP-Key": "YOUR KEY" } } } } Prefer to sign in instead of using a key? Replace headers with "oauth": { "enabled": true } and run /mcp auth contentin in Gemini CLI. 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 where you created it and create a new one: on the ContentIn for Agents page https://app.contentin.io/agents under Connect your AI, or on Growth and Pro under Profiles → Connections https://app.contentin.io/profiles?tab=connections . Revoking takes effect immediately. Keys only go in the header. Putting a key in the URL is no longer documented, because credentials in URLs end up in logs and browser history; connectors already set up that way keep working until you reconnect. Thirteen tools. Your assistant picks the right one from what you ask, so you never call them by name. get account status Your setup, plan and what each tool needs. Works on any connected account, with or without a plan, so your assistant can tell you what is missing and where to fix it. list posts Drafts, scheduled posts, published posts and saved ideas, filtered by status, date or a search term. get post analytics Impressions, members reached, reactions, comments, shares and engagement rate for a published post. list my comments The comments you wrote on other people's posts, newest first, with the comment's URN and a direct link, the likes and replies it got, and the post it sits under with its author. Filter by date range or a search term, up to 100 at a time. Read from a daily sync, so the last day can still be missing; history starts when your profile became a paying account with a LinkedIn URL on file. Who reacted to a comment isn't available, only the counts. list leads Everyone who reacted to, commented on or shared your own posts: name, headline, profile URL, ContentIn's ICP fit score, lead status, their recent comments and the posts that pulled them in. Filter by lead status, minimum score or last interaction, sort by any of the three, up to 100 at a time. A single reaction is enough to create a lead; an unscored lead means ContentIn hasn't scored it yet, not that they're a poor fit. get voice context Your writing guide and language, your rules your own, the ones learned from your edits, always/never and guardrails , your saved stories, opinions, numbers and frameworks, your best posts and your strategy, so your own assistant writes like you. Pass a topic and the material is matched to it; each item says where it came from. Read-only: nothing is written or posted. write post in my voice Brain-dump the raw material and get back a draft built on the voice model trained on your own posts. repurpose post Take a post that landed and rework it from a fresh angle instead of repeating yourself. generate ideas Post ideas drawn from your topics, your audience and what has already resonated for you. capture substance Ask your AI to save a story, an opinion or a number into your substance bank, so future drafts can draw on it. Nothing is saved unless you ask. attach images Add up to 5 images to a draft a public image URL or the file itself , then publish or schedule it as usual. JPG, PNG or WEBP, 8 MB each; one image goes out as a single image, two or more as a LinkedIn multi-image post. GIFs, video and PDFs aren't supported. Fair use: 30 images an hour and 100 a day per key. schedule post Queue a post for a specific time. Shows you the exact text and waits for your confirmation first. publish post Publish immediately. Shows you the exact text and always waits for your confirmation. 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. An assistant can't quietly queue something behind your back. Each connected app and each API key acts for one ContentIn profile and carries no access to anything else on your account. Your LinkedIn password is never involved. Publishing is a separate permission your client asks for the first time it publishes. Revoke a connection or key at any time and it stops working immediately: on the ContentIn for Agents page under Connect your AI, or on Growth and Pro under Profiles → Connections. Each connection 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 you connected. That means access is always accurate. If you upgrade, the tools start working without you doing anything. A connected app can only reach the one ContentIn profile you picked when you approved it: that profile's posts, drafts, ideas, analytics, comments and leads, within the permissions you granted. It can't see your other profiles, your billing details or your LinkedIn password. What the app does with the data it reads is governed by that app's own terms. You can see every connected app and revoke its access at any time. On ContentIn for Agents, that's the ContentIn for Agents page https://app.contentin.io/agents under Connect your AI. On Growth or Pro, it's Profiles → Connections https://app.contentin.io/profiles?tab=connections . Revoking takes effect immediately. For how ContentIn handles your data, read our privacy policy https://www.iubenda.com/privacy-policy/58097432 . Create a free ContentIn for Agents https://contentin.io/linkedin-for-ai-agents/ account, no card needed. Your AI can schedule and publish to LinkedIn right away, 2 posts a day and 30 a month per profile. Add the Agent plan from $29 a month when you want your analytics, your full voice profile and ContentIn's writing. Want the full ContentIn web app as well? The MCP server is included in Growth and Pro https://contentin.io/pricing/ . New to the Model Context Protocol? Read the LinkedIn MCP definition https://contentin.io/glossary/linkedin-mcp/ in our glossary, or try the free AI LinkedIn post generator https://contentin.io/ai-linkedin-post-generator/ first. No login required.