Purpose
linkedapi-mcp is an MCP (Model Context Protocol) server designed to connect LinkedIn accounts to AI assistants such as Claude, Cursor, VS Code, and Windsurf, enabling AI to control LinkedIn accounts and obtain real-time data. Users can have the AI assistant search for potential customers, send messages, and analyze profiles, all completed securely and automatically through a cloud browser.
Main Capabilities
- Sales Automation Assistant: Enables AI to find leads, check profiles, and draft personalized outreach messages. For example, search for "software engineers at companies with 50-200 employees in San Francisco," analyze their backgrounds, and suggest appropriate contact messages.
- Recruiting Assistant: Search for candidates with specific skills, review their experience, and send initial outreach, handling time-consuming steps so recruiters can focus on communicating with candidates.
- Conversation Assistant: AI can read existing LinkedIn conversations and help reply naturally, understand chat context, suggest relevant replies, and even send follow-up messages.
- Market Research Assistant: Collect data on companies, employees, and recent activity, perform competitor analysis, and gain industry trend insights without spending a lot of time on LinkedIn.
How to Use
Officially, three getting-started guides are provided (about a 2-minute read):
- Installation: Set up MCP in Claude, Cursor, VS Code, or Windsurf.
- Available tools: Explore all LinkedIn tools that the AI assistant can call.
- Usage examples: View real examples to get started quickly.
Long-Running Operations
Linked API operations run through a cloud browser and are queued like ordinary automation. Many operations take several minutes, especially searches and profile retrieval with optional data.
If a tool returns status、workflowId、operationName and message, it means the operation is still running. Do not retry the original tool, as this may queue duplicate work. Instead, use the exact workflowId and operationName to call get_workflow_result, until the final result is returned. By default,get_workflow_result will poll for a long time until the workflow completes or the current MCP client's request budget is exhausted; pass in waitSeconds: 0 to get an immediate single snapshot.
Applicable Scenarios
- Sales teams automating lead generation and outreach
- Recruiters screening candidates and making initial contact
- Managing existing LinkedIn conversations and sending follow-ups
- Collecting company and industry data for market research
Limitations
- Specific installation steps, the complete list of available tools, and usage examples require reference to the official guides; detailed content is not provided in the current materials.
- Operations depend on a cloud browser queue for execution and may take a long time.
- When a call returns an intermediate status, do not retry the original tool; obtain the workflow result in the specified way.
License
This project uses the MIT License. For details, see the LICENSE file.
