Skip to main content

​
What is MCP?

The Model Context Protocol (MCP) is an open standard for connecting AI assistants to external tools and data sources. LexQ CLI includes a built-in MCP server that exposes the entire LexQ API as 53 tools. When connected, AI agents can manage your policies directly:
  • “Create a discount rule for VIP customers”
  • “Dry-run this version with payment_amount=200000”
  • “Run a batch simulation comparing v3 and v4”

​
Quick Start

  1. Node.js 18+ installed
  2. Run lexq auth login once to store your API key
  3. Start the server:
lexq serve --mcp
The MCP server uses the same API key and base URL from ~/.lexq/config.json. No additional authentication setup is needed.

​
Setup Guides

​
Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
  "mcpServers": {
    "lexq": {
      "command": "npx",
      "args": ["-y", "@lexq/cli", "serve", "--mcp"]
    }
  }
}
Restart Claude Desktop after editing.

​
Claude.ai (Web)

Go to Settings → MCP Servers → Add, set Command: npx, Args: -y @lexq/cli serve --mcp.

​
VS Code / Cursor

Create .vscode/mcp.json (or .cursor/mcp.json): 
{
  "servers": {
    "lexq": {
      "command": "npx",
      "args": ["-y", "@lexq/cli", "serve", "--mcp"]
    }
  }
}

​
Windsurf / Other MCP Clients

{
  "mcpServers": {
    "lexq": {
      "command": "npx",
      "args": ["-y", "@lexq/cli", "serve", "--mcp"]
    }
  }
}

​
Available Tools — 53

DomainToolsDescription
Status1lexq_whoami
Groups8CRUD + A/B test
Versions6CRUD + clone
Rules7CRUD + reorder + toggle
Facts4CRUD
Deploy7publish, live, rollback, undeploy, history, detail, overview
Analytics8dry-run, compare, requirements, simulation × 5
History3list, get, stats
Integrations5list, get, save, delete, config-spec
Logs4list, get, action, bulk-action

​
Agent Best Practices

  1. Read skills first. Have the agent read skills/lexq-shared/SKILL.md before any task.
  2. Follow the standard workflow. Create group → version → facts → rules → dry-run → publish → deploy.
  3. Always dry-run before publishing.
  4. Handle the response envelope. Check result === "SUCCESS" — not success === true.

​
Troubleshooting

​
”Error: API key not found”

Run lexq auth login before starting the MCP server.

​
MCP server starts but tools aren’t visible

Restart your AI client after adding the MCP configuration.

​
Connection timeout

The MCP server uses stdio transport — it doesn’t open network ports. Ensure your client supports stdio transport.

​
Next Steps

Command Reference

Full list of all CLI commands mapped to MCP tools.

Policy Rules

Condition syntax and action types for rule creation.