For AI agents

Coding agents like Codex, Claude Code, and Cursor change APIs faster than anyone can review by hand. An agent cannot trust its own grade: the check has to come from outside the generation loop. Dino is that check. The agent builds, Dino verifies the running API and returns a deterministic verdict, and the agent branches on it with no human in the middle.

How an agent calls Dino

Two interfaces, same verdict. The CLI needs no account: run dino scan --format json against any endpoint, read the verdict on stdout and the branch signal from $?. The MCP server is the hosted path: typed tools plus history, gates, and comparison.

dino scan --endpoint https://your-api.com/graphql --fail-on-high --format json --quiet

An agent reads three surfaces, in the order it acts on them:

1. Exit code (branch): 0 clean · 2 usage · 3 policy gate failed · 4 transient · 5 config · 6 partial · 70 crash. Branch on $? with no parsing. See exit codes.
2. JSON verdict (understand): --format json emits ScanResultV1 on stdout (core.health.verdict, findings, coverage); stdout stays pure, so it pipes to jq. See JSON output.
3. Error envelope (recover): on exit 2/4/5/70, the last stderr line is {"error":{"kind","message","retryable","exitCode"}}. retryable says retry (transient) or stop (permanent). See error envelopes.

Is the change safe to ship?

dino scan --fail-on-high exits 3 when any HIGH or CRITICAL finding exists and 0 when clean, enough to decide continue-or-stop. Over MCP, get_agent_readiness returns status: ready | partial | not_ready | degraded with a per-dimension breakdown, so the agent knows what to fix first.

Connect over MCP

Add @dino-hq/mcp-server to your MCP client with a DINO_API_KEY (a dino_k_live_… tenant key). It runs over stdio and scopes every call to that tenant.

{
  "mcpServers": {
    "dino": {
      "command": "npx",
      "args": ["-y", "@dino-hq/mcp-server"],
      "env": { "DINO_API_KEY": "dino_k_live_..." }
    }
  }
}

The core loop: run_scan (non-blocking) → poll get_scan_result → get_findings / get_agent_readiness → decide. compare_scans diffs two runs and evaluate_quality_gate checks a configured gate. Read-only tools work for any caller; write and admin tools need an OAuth (owner/admin) login.