Agent Integration

Cekura is designed to work seamlessly with AI coding agents. Whether you’re using Claude Code, Cursor, or VS Code, you can manage your voice agent testing and observability directly from your development environment.

Integration Options

MCP & Skills

Install Cekura Skills so your assistant knows Cekura workflows, plus the MCP server so it can act on your workspace. Recommended setup.

AGENTS.md preset

Portable fallback: drop an AGENTS.md file in your repo for assistants that don’t load Agent Skills.

Quick Setup

1. Install Skills, then connect MCP

First install Cekura Skills so your assistant knows Cekura workflows:

npx skills add cekura-ai/cekura-skills --all

Claude Code users: install the plugin instead — it bundles Skills, slash commands, and MCP config in one step. See MCP & Skills setup.

Then connect the MCP server so your assistant can act on your workspace:

Claude Code
Cursor / VS Code

claude mcp add --transport http cekura --scope user https://api.cekura.ai/mcp

OAuth opens a browser to sign in — no API key needed. For API-key auth, see API-key setup.

Add to your MCP config (see manual setup):

{
  "mcpServers": {
    "cekura": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.cekura.ai/mcp"]
    }
  }
}

2. Add AGENTS.md to Your Repo

Drop an AGENTS.md template into your project root. This teaches any AI assistant the Cekura-specific workflows and terminology for your project.

3. Discover Documentation

Cekura’s documentation is available in agent-friendly formats:

Resource	URL	Purpose
llms.txt	`https://docs.cekura.ai/llms.txt`	Page index with descriptions for AI discovery
llms-full.txt	`https://docs.cekura.ai/llms-full.txt`	Full documentation content in markdown
OpenAPI Spec	`https://api.cekura.ai/api/schema/`	Complete API specification

Common Agent Workflows

Test Your Agent After a Deploy

User: "Run our regression tests against the staging agent"

AI: [Uses list-agents, then scenarios-run-scenarios-create]
"I've kicked off 12 scenarios against your staging agent.
Results will be ready in ~3 minutes. I'll check the results."

Create Metrics from Agent Description

User: "Generate quality metrics for our customer support agent"

AI: [Uses metrics-generate-metrics-create]
"I've generated 5 metrics based on the agent's system prompt:
1. Greeting Quality (boolean)
2. Issue Resolution (boolean)
3. Empathy Score (numeric 1-5)
4. Policy Compliance (boolean)
5. Call Wrap-up Quality (boolean)"

Review Call Quality

User: "Show me the worst performing calls from last week"

AI: [Uses call-logs-list with filters]
"Here are the 5 lowest-scoring calls from the past 7 days..."

Generate Evaluators from Real Calls

User: "Create test scenarios from our recent support calls"

AI: [Uses call-logs-create-scenarios-create]
"I've created 8 test scenarios from your recent call logs.
Each scenario captures the conversation flow and expected outcomes."

Best Practices

Start with read-only operations

Begin with listing agents, viewing results, and reading call logs before using write operations like creating metrics or running scenarios.

Use project scoping

If you have multiple projects, always specify the project_id parameter to scope your queries. This prevents cross-project data leakage.

Monitor context window usage

Large responses (detailed transcripts, full result sets) can consume significant context. Use pagination parameters (page, limit) to control response size.

Combine with CI/CD

Use Cekura’s GitHub Actions integration alongside MCP to run evals on every PR and review results from your agent.

Next Steps

Manual setup (Skills + MCP)

Install Skills, then configure the MCP server — for clients without a plugin

AGENTS.md Template

Copy-paste template for your project

API Reference

Complete API documentation

Testing Guide

Learn how to create and run evaluators

Get Started

Key Concepts

Guides

Integrations

Advanced

Agent Integration

Integration Options

MCP & Skills

AGENTS.md preset

Quick Setup

1. Install Skills, then connect MCP

2. Add AGENTS.md to Your Repo

3. Discover Documentation

Common Agent Workflows

Test Your Agent After a Deploy

Create Metrics from Agent Description

Review Call Quality

Generate Evaluators from Real Calls

Best Practices

Next Steps

Manual setup (Skills + MCP)

AGENTS.md Template

API Reference

Testing Guide

​Integration Options

MCP & Skills

AGENTS.md preset

​Quick Setup

​1. Install Skills, then connect MCP

​2. Add AGENTS.md to Your Repo

​3. Discover Documentation

​Common Agent Workflows

​Test Your Agent After a Deploy

​Create Metrics from Agent Description

​Review Call Quality

​Generate Evaluators from Real Calls

​Best Practices

​Next Steps

Manual setup (Skills + MCP)

AGENTS.md Template

API Reference

Testing Guide

Integration Options

Quick Setup

1. Install Skills, then connect MCP

2. Add AGENTS.md to Your Repo

3. Discover Documentation

Common Agent Workflows

Test Your Agent After a Deploy

Create Metrics from Agent Description

Review Call Quality

Generate Evaluators from Real Calls

Best Practices

Next Steps