Getting More Out of Coval with Claude (MCP Guide)
If you already use the Coval UI, you know how much you can do — but there’s a faster way to work. Coval’s MCP server connects Claude directly to your Coval workspace, so you can create and manage evaluations just by describing what you want. No clicking through menus. No copy-pasting prompts. Just tell Claude what you need.What you can do
Build test sets faster
Instead of manually entering test cases one by one, describe your scenarios to Claude: “Create a test set for a billing support bot — include cases for refund requests, subscription changes, and payment failures.” Claude generates and adds them directly to your workspace.Create and refine metrics
Describe the behavior you want to evaluate in plain language. Claude can draft a Composite Evaluation criteria set, and you can iterate on it conversationally until it captures exactly what matters.Trigger simulation runs
Ask Claude to kick off a run against a specific agent and test set. No need to navigate to the UI — Claude handles it and can summarize results when it finishes.Check results and debug
Ask “which test cases are failing?” or “what’s the pass rate on my escalation metric?” Claude pulls the data and explains what it finds.How to get set up
MCP requires Claude Desktop (the downloadable app) — it doesn’t run in the browser at claude.ai.Option 1: Via the app
- Download Claude Desktop at anthropic.com/download
- Open Settings → Developer → Edit Config
- Paste in the Coval MCP server config (copy from the Coval docs — link below)
- Restart Claude Desktop
Option 2: Via terminal
mcpServers section:

