Reads · run at once
- Get ad targeting facets
- Get audience counts
- Get company info
- Get group definition
- Get image details
- Get images
- Get my info
- Get network size
Give Claude Code, Cursor, Codex or your own agent LinkedIn through one MCP URL and one key. Your team signs in to LinkedIn once and the agent never holds a token. Reads run at once; anything that changes LinkedIn waits for your approval.
Actions
A sample of the 29 actions. Your agent sees the full list with tools/list.
Quickstart
Claude Code · Terminal
claude mcp add --transport http vellarin https://hub.vellarin.ai/api/hub/mcp --header "Authorization: Bearer <key>"Cursor · ~/.cursor/mcp.json (or .cursor/mcp.json in a project)
{
"mcpServers": {
"vellarin": {
"url": "https://hub.vellarin.ai/api/hub/mcp",
"headers": {
"Authorization": "Bearer ${env:VELLARIN_HUB_KEY}"
}
}
}
}Codex · ~/.codex/config.toml
[mcp_servers.vellarin]
url = "https://hub.vellarin.ai/api/hub/mcp"
bearer_token_env_var = "VELLARIN_HUB_KEY"Questions
Create a free Vellarin account, connect LinkedIn with its normal sign-in, create an agent key on the Developers page and add the Vellarin Hub MCP server to your client with one line. Your agent then sees the LinkedIn actions as tools.
No. Read actions run at once. Any action that sends, creates, changes or deletes something in LinkedIn waits for the workspace owner's approval and then runs exactly once.
No. The sign-in lives on the server side. Your agent holds only a Vellarin Hub key, which you can scope to LinkedIn alone, cap per day and per month, and revoke at any moment.
Hub Free includes 500 app calls a month and 1 agent key, with no card. Over the cap the answer is "upgrade or wait", never a charge.
LinkedIn is a trademark of its owner. Vellarin Hub is an independent product and is not affiliated with or endorsed by it.