SDK Quickstart
Install
@pecta/core and run your first gate evaluation in minutes.MCP Proxy
Wrap any MCP server with quality gates using a single CLI command.
REST API
Evaluate agent output from Python, Go, or any HTTP client.
API Reference
Explore all endpoints, request schemas, and response formats.
How Pecta works
Pecta evaluates agent outputs through three integration modes — pick the one that fits your stack:1
Choose your integration mode
Pick the SDK for Node.js workloads, the MCP proxy for Claude Desktop or Cursor, or the REST API for any other language.
2
Configure your gates
Select from built-in gates (latency, schema, filesystem, PII, content) or write custom gates for your domain logic.
3
Evaluate agent output
Every
engine.evaluate() call returns a pass/fail verdict with per-gate details in under 15ms.4
Track reputation over time
Telemetry ships async to the Pecta cloud, building a 0–1000 reputation score for each agent across the last 500 evaluations.
Key features
Quality Gates
Parallel, fail-fast gate evaluation with a configurable timeout budget. Works on the first request — no training period needed.
Reputation Scores
Portable 0–1000 score per agent, computed from pass rate, latency, streaks, and volume over 500 evaluations.
RTB Gates
OpenRTB-aware gates for ad exchanges: tmax guard, impid match, adomain verify, bid sanity, audience safety, bcat compliance.
Custom Gates
Bring your own pass/fail logic with a simple
{ name, run } interface. No framework lock-in.Privacy by Design
Pecta never stores bid payloads, MCP tool inputs, or user content. Only metadata ships to the cloud.
Real-time Dashboard
Live event feed, agent score trajectories, gate analytics, and aggregate org stats.