Skip to main content
Coval works with any AI coding agent. Whether you use Claude Code, Cursor, Windsurf, Codex, or another tool, your agent can run evaluations, manage test sets, and score AI outputs through the interface that fits your workflow.

​
Get Started

Agent Skills

Install evaluation expertise with one command. Your agent learns how to build test sets, select metrics, and run evals.

Guided Onboarding

Run /onboard and your agent walks you through setting up a complete evaluation from scratch.

MCP Server

Connect the Coval MCP server for native tool access in Claude Desktop, Cursor, and other MCP clients.

CLI

The Coval CLI gives agents structured JSON output for scripting evaluations in any terminal.

​
Three Ways Agents Use Coval

LayerWhat It DoesInstall
Agent SkillsTeaches agents how to evaluate well (knowledge)npx skills add coval-ai/coval-external-skills
MCP ServerGives agents tools to execute evaluationsnpx coval-mcp
CLIRuns evaluations from any terminal with JSON outputbrew install coval-ai/tap/coval
Skills and MCP are complementary — Skills give your agent the expertise to design good evaluations, while MCP and CLI let it execute them. Use whichever combination fits your workflow.

​
Supported Agents

Claude Code

Skills + MCP + CLI

Cursor

Skills + MCP

Windsurf

Skills + MCP

Codex

Skills + CLI

GitHub Copilot

CLI + API

Any Agent

CLI + API

​
AI-Readable Documentation

Coval publishes machine-readable documentation following the llms.txt standard:
  • llms.txt — Curated index of all documentation pages (~7KB)
  • llms-full.txt — Complete documentation in a single file (~386KB)
Point your agent at these files when it needs context about Coval’s platform, API, or concepts.