Skip to main content
The OpenCX server connects your account to AI clients like Cursor, Claude Desktop, Claude Code, Visual Studio Code, Windsurf, and Zed. Manage contacts, sessions, training, workflows, and analytics through natural language — without switching to the dashboard.
New here? Head to Get Started to connect your first AI client.

​
What You Can Do

Pull session history, reassign conversations, resolve tickets, and reply — without leaving your editor. Filter by status, sentiment, tags, or team.
Create and edit training scenarios, search the knowledge base, organize training into directories, and crawl websites to keep content current.
Configure API actions your AI agent calls during conversations. Trigger workflows, manage outbound sequences, and set up phone agents.
Review handoff reasons, CSAT scores, SLA compliance, and recurring support themes. Pull impact reports and customer insights by category.

​
Two ways to connect

  • Remote (no install) — connect straight to https://api.open.cx/mcp over Streamable HTTP with your API key as a bearer token. Nothing to install or update. See Remote server.
  • Local — run the server yourself via npx @opencx/mcp (stdio). Works with every MCP client and self-hosted deployments.
Both expose the same tools.

​
Requirements

  • An OpenCX API key — generate one in your OpenCX dashboard under Settings > API Keys
  • Node.js 18 or later — only for the local npx @opencx/mcp setup; the remote endpoint needs nothing installed

Get Started

Connect the MCP server to your AI client

Prompt Library

Ready-to-use prompts by domain

Tools Reference

All available tools organized by domain

Troubleshooting

Common issues and how to resolve them