LinkedIn MCP for Cursor: connect LinkedIn and X to Cursor

To connect LinkedIn and X to Cursor, add Flaghand's MCP server to ~/.cursor/mcp.json and sign in:

{
  "mcpServers": {
    "flaghand": { "url": "https://app.flaghand.com/mcp" }
  }
}

Then open Customize in Cursor's sidebar and sign in to Flaghand where it's listed with your MCP servers. Cursor's agent can then draft LinkedIn and X posts from your project and send them to you for approval. You approve each exact post with your passkey, and Flaghand posts it.

Checked on October 28, 2026, against Cursor's MCP docs and Flaghand's setup docs, linked under Sources.

Connect it in four steps

1. Get a Flaghand account and connect your accounts. Start here, then connect your LinkedIn profile and X account under Settings › Account. Each network shows its own sign-in; Flaghand never asks for your LinkedIn password or browser cookies.

2. Add the server. Merge the JSON above into ~/.cursor/mcp.json for every project, or .cursor/mcp.json in one project's folder. If the file already lists servers, add flaghand beside them. No header or API key is needed.

3. Sign in. Open Customize in the sidebar and sign in to Flaghand. Flaghand's page opens in your browser: sign in with your passkey, Google or email and click Allow (pick the workspace first if you have more than one).

4. Ask for a post. In the agent chat, try:

   Use Flaghand: draft a LinkedIn post about the feature in this branch, and send it to me for approval.

Cursor asks before it uses an MCP tool. Allowing that lets the agent save a draft or ask for your approval; it isn't the approval to post. The agent writes the post, Flaghand checks it against LinkedIn's rules, and the agent gives you an approval link. Open it on your phone or computer, look at the post as LinkedIn will show it, and approve with Face ID, Touch ID or a security key. Nothing posts until you do.

In Cursor's CLI

Cursor's CLI reads the same mcp.json. From the project folder you'll use it in:

agent mcp login flaghand
agent mcp list-tools flaghand

The CLI keeps its sign-in per project folder, so run it from the same folder each time.

What Cursor can and can't do through Flaghand

The sign-in gives Cursor four scopes: read, drafts, media and request-approval. No scope can approve, schedule or post, so Flaghand's server refuses Cursor if it tries. Flaghand posts to LinkedIn only through LinkedIn's official API and only to your personal profile. It doesn't read profiles, your feed, messages or jobs.

Questions

Is there an X (Twitter) MCP for Cursor? The same server drafts X posts and threads. One approval can cover a whole plan, such as an X thread and a LinkedIn post together.

Can Cursor post without my approval? No. Approving takes your passkey, and no Flaghand token can approve, schedule or post. Turning off Cursor's tool prompts doesn't change that.

Can I use a token instead of signing in? Yes. Create one in Flaghand under Settings › Agents › Create token and add "headers": { "Authorization": "Bearer ${env:FLAGHAND_TOKEN}" } to the flaghand entry, with FLAGHAND_TOKEN set from your secret store. Signing in is simpler.

How do I take Cursor's access away? In Flaghand, open Settings › Agents and click Revoke. Or delete the flaghand entry from mcp.json.

Other apps

The same server works in Claude, ChatGPT, Claude Code, Codex and Gemini. The LinkedIn MCP server explains what Flaghand does on LinkedIn; the X MCP server and the X API and MCP servers, compared covers X, and Flaghand compared sets it beside other schedulers and posting APIs.