# Averta

**Canonical:** https://apis.io/providers/averta-io/  
**Website:** https://averta.io/  
**APIs profiled:** 1

Averta provides an agentic AI security platform, the AI Agent Operating System, which classifies, governs, and audits every prompt, tool call, and action to ensure safe execution of enterprise AI agents. The operating system offers comprehensive controls, policy enforcement, and audit trails for AI workloads, helping organizations mitigate risks associated with advanced language models.

## Kin Score — 36.3 / 100 (thin)

Scored 2026-11-02 under rubric 0.26.0.

| Facet | Score |
|---|---|
| Discoverability | 65.0 |
| Contract Quality | 45.5 |
| Contract Governance | 22.0 |
| Operational Transparency | 7.9 |
| Developer Ergonomics | 46.9 |
| Access Clarity | 21.1 |

Regulatory layer — **Horizontal (data, software, accessibility, platform)**: 22.7 (matched via fallback).

## Agent readiness — 49.1 (agent-ready)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | documented |
| Auth Clarity | served |
| Idempotency | no |
| Error Semantics | derived |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | yes |
| Agent Skills | unknown |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | conformant |
| Dry Run Mode | no |
| Delegated Identity | served |
| Protected Resource Metadata | verified |
| Dynamic Client Registration | yes |
| Agentic Commerce | no |
| Pagination Ratio | na |
| Operation Distinctiveness | na |
| MCP Tool Quality | na |

## Access

Unknown — onboarding: unknown, pricing: unknown, trial: no (confidence: low).

## APIs (1)

- **Averta Runtime Decision API** — The Averta runtime decision API.

## MCP servers (1)

- **Averta MCP Server** — Remote MCP server at docs.averta.io.

## Security (1)

- **Averta Io Domain Security** — TLSv1.3 · HSTS · DMARC

## Tags

Artificial Intelligence, Security, AI Agents, Enterprise, Platform

---

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