Linkedin MCP server
{
"mcpServers": {
"mcp-linkedin": {
"type": "http",
"url": "https://linkedin.run.mcp.com.ai/mcp"
}
}
}{
"mcpServers": {
"mcp-linkedin": {
"type": "http",
"url": "https://linkedin.run.mcp.com.ai/mcp"
}
}
}{
"mcpServers": {
"mcp-linkedin": {
"type": "http",
"url": "https://linkedin.run.mcp.com.ai/mcp"
}
}
}{
"servers": {
"mcp-linkedin": {
"type": "http",
"url": "https://linkedin.run.mcp.com.ai/mcp"
}
}
}{
"mcpServers": {
"mcp-linkedin": {
"type": "http",
"url": "https://linkedin.run.mcp.com.ai/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 1.0.0+0.7.1
What it does
This is a framework that converts OpenAPI specifications into MCP servers automatically, rather than a server for LinkedIn specifically. It allows developers to expose any REST API as MCP tools without rewriting business logic.
- Transform existing REST APIs into MCP tools that work with AI clients like ChatGPT and Claude
- Expose internal APIs to agents and LLMs while maintaining existing authentication, rate limits, and governance
- Orchestrate multi-step API workflows through MCP clients without custom integration code
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.