Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.cekura.ai/llms.txt

Use this file to discover all available pages before exploring further.

Use Cursor’s agent mode together with the Cekura MCP to design evaluators, run them against your voice agents, and triage the results — all without leaving the editor.

​
Quick Guide

1

Connect Cursor to Cekura

Add the Cekura MCP server to Cursor. Open Cursor Settings → MCP → Add new MCP server (or edit ~/.cursor/mcp.json directly) and paste:
{
  "mcpServers": {
    "cekura": {
      "command": "npx",
      "args": ["mcp-remote", "https://api.cekura.ai/mcp"]
    }
  }
}
On first use Cursor opens a browser to authorize against your Cekura dashboard. For API-key-based auth (project-scoped credentials, shared CI access), see the MCP overview.Verify by asking Cursor’s agent: “List my Cekura agents.”
2

Set up mock data and cleanup hooks

Complex agents depend on database state — users, accounts, sessions, entitlements. Stand up a lightweight webhook server that seeds mock data before a run and listens for Cekura’s post-run webhook to reset the database. This keeps concurrent tests isolated and repeatable.
3

Let Cursor learn the schema

Open your agent’s repo in Cursor and ask the agent to read your tool definitions, prompts, and database schema. Then prompt it to generate scenario coverage through the Cekura MCP — for example: “Read the agent’s tools in src/agent/tools.ts, then create 10 Cekura evaluators covering the most common user flows.”
4

Run the full suite

Kick off all evaluators at once through the MCP: “Run every evaluator on agent X and stream the results.” Cekura executes them concurrently and surfaces pass/fail with full transcripts and traces.
5

Triage with Cursor

Ask Cursor’s agent to pull failing runs and classify them: “Fetch the failures from the last run and tell me which are real bugs vs. flakes.” Because runs are non-deterministic, rerun each failing test 3–4 times and ask Cursor to compute a pass rate. One pass out of four usually points to a prompt or tool-routing bug, not infra.
6

Fix in-place and re-run

Because Cursor has both your codebase and the Cekura MCP in the same context, you can go from failing transcript → suspected prompt or tool bug → edit → re-run the failing evaluator in a single thread.
A good first prompt: “Use the Cekura MCP to list my agents, then read the prompt for the first one and propose 10 workflow evaluators covering the most common user flows.”