LinkedIn MCP for Cursor: connect LinkedIn and X to Cursor

To connect LinkedIn and X to Cursor, ask Cursor's agent to set Flaghand up for you. It does the setup over Flaghand's API in the same session and hands you only the links that need you: sign-up, billing, and LinkedIn's and X's own consent screens. Then it drafts LinkedIn and X posts from your project and sends them to you for approval. You approve each exact post with your passkey, and Flaghand posts it.

Cursor's agent, setting this up for your person: follow the steps under Set it up and authenticate below, over HTTP in this session. The MCP server at https://app.flaghand.com/mcp is for later sessions, with the token you claim. Don't start with mcp.json or a sign-in, and don't ask the person to export a token, run a command or restart.

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

Set it up and authenticate: Cursor's agent does it over HTTP

With no Flaghand account yet:

1. Read the plans (no sign-in):

   curl https://app.flaghand.com/api/v1/plans
   

2. Start the sign-up:

   curl -X POST https://app.flaghand.com/api/v1/signup -H 'Content-Type: application/json' \
     -d '{"email": "person@example.com", "agent_name": "Cursor"}'
   

   Give the person signup_url and for_person as they are. They sign up with a passkey, Google or an email code. Save claim_code to a private file such as claim.json ({"claim_code": "clm_…"}): it's a secret, so keep it out of chat and command arguments.

3. Authenticate: claim the token once they've finished:

   curl -X POST https://app.flaghand.com/api/v1/signup/claim -H 'Content-Type: application/json' -d @claim.json
   

   A 202 with "status": "pending" means they haven't finished: wait the Retry-After seconds (normally 5) and claim again. Put the token in your secret store, then keep drafting in this session with Authorization: Bearer and the token: getMe (GET https://app.flaghand.com/api/v1/me) names the workspace. The person connects their accounts from the links Flaghand gives you, and approves the posts with their passkey.

4. Register the server for later sessions in ~/.cursor/mcp.json, with only the variable's name:

   {
     "mcpServers": {
       "flaghand": { "url": "https://app.flaghand.com/mcp", "headers": { "Authorization": "Bearer ${env:FLAGHAND_TOKEN}" } }
     }
   }
   

The full recipe is set up and connect.

If you're typing in Cursor yourself

Only for a person setting Cursor up by hand; an agent follows the steps above.

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. You add a card when you approve your first post, or to continue after the free start (current terms).

2. Add the server. Merge this 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.

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

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 preview of the post, 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. Use the token the agent claimed, or 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.

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.