# Archal

**Canonical:** https://apis.io/providers/archal/  
**Website:** https://docs.archal.ai  
**APIs profiled:** 5

Archal is a Y Combinator (S26) company building QA and an improvement loop for AI agents. It provisions hosted, service-shaped CLONES of real SaaS services — GitHub, Slack, Stripe, Jira, Linear, Supabase, Ramp, HubSpot, Datadog, Discord, Google Workspace and more — so an agent that can send emails, change code repositories, or call third-party APIs is tested and scored before it touches production. Clones hold state, enforce referential integrity, and return authentic error shapes, unlike traditional mocks. Its Autoloop turns real production agent traces into reproducible failures and can open a fix PR. Archal ships an npm CLI and Vitest SDK, a device-auth login, a runtime clone proxy, and per-session MCP endpoints.

## Kin Score — 39.1 / 100 (thin)

Scored 2026-08-17 under rubric 0.11.0. Trend: flat (+0.0 from 39.1).

| Facet | Score |
|---|---|
| Discoverability | 81.5 |
| Contract Quality | 55.2 |
| Governance | 11.5 |
| Operational Transparency | 5.3 |
| Developer Ergonomics | 75.5 |
| Commercial Clarity | 0.0 |

## Agent readiness — 47.1 (agent-native)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | derived |
| MCP Server | yes |
| Auth Clarity | yes |
| Idempotency | documented |
| Error Semantics | documented |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | derived |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Self-serve signup — onboarding: self-serve, pricing: unknown, trial: no (confidence: medium).

## APIs (5)

- **Archal Auth API** — CLI and device authentication.
- **Archal Catalog API** — Clone and scenario discovery.
- **Archal Results API** — Run, trace, and test-result reporting.
- **Archal Runtime API** — Direct calls into a running clone.
- **Archal Sessions API** — Hosted clone session lifecycle.

## MCP servers (1)

- **archal-mcp.yml**

## Agentic access (1)

- **Archal Agentic Access** — 16 operations · 7 acting · 1 human-in-the-loop

## Security (2)

- **Archal Authentication** — apiKey/http · 2 schemes
- **Archal Domain Security** — TLSv1.3 · DMARC

## Tags

Company, AI Agents, Agent Testing, Developer Tools, API Testing, Sandbox, Evaluation, Infrastructure

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/archal/). Scores are computed from the provider's own public artifacts under a published rubric.