Agent Tools
Back to MCP servers
● degraded

The Periodix Actions MCP server lets AI agents search LinkedIn and Sales Navigator using plain text. No workflow builder, no HTTP configuration, no orchestrator. Describe what you need in natural language and the agent returns structured results. This works with any MCP-compatible client: Claude Code, Claude Desktop, Cursor, Windsurf, or your own implementation. Built by the team behind [Periodix](https://periodix.net), an AI sales agent for LinkedIn rated **4.9/5 on G2**. Periodix has been working with LinkedIn's infrastructure since 2023, and the MCP server is the fastest way to give your AI agent direct access to LinkedIn search. --- ## Example prompts your agent can handle - *"Find 4 DevOps engineers from Germany who work at companies with 50 to 100 employees in the SaaS industry."* - *"Who posted about Web Summit from France yesterday?"* - *"Search Sales Navigator for marketing directors at fintech companies in London with 200+ employees."* - *"Find open product manager jobs at Series B startups in New York."* - *"Show me people who posted about hiring a Head of Sales this week in the US."* - *"Find job posts for senior data engineers published in the last 7 days at companies with 500+ employees."* --- The MCP server accepts the same search types as the HTTP API: People, Companies, Posts, and Jobs on LinkedIn Classic, plus People and Companies on Sales Navigator. The difference is that you describe the search in words, and the agent constructs the query for you.

Transport
streamable-http
Auth
smithery_api_key
Cost

How to connect

MCP endpoint (streamable-http)
https://server.smithery.ai/info-pywu/periodix-actions/mcp
JSON-RPC initialize probe
curl -X POST https://server.smithery.ai/info-pywu/periodix-actions/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'
Homepage
https://periodix.net/developers
Listed at (smithery)
https://periodix.net/developers