# Waxell

**Canonical:** https://apis.io/providers/waxell/  
**APIs profiled:** 6

Waxell is an AI agent governance and observability platform that provides runtime policy enforcement, auto-instrumented LLM telemetry, MCP governance, cost management, and durable workflow execution for agents built in any Python framework or third-party agentic tool (Claude Code, Cursor, LangChain, CrewAI, OpenAI Agents SDK, and 200+ more).

## Kin Score — 61.4 / 100 (strong)

Scored 2026-08-25 under rubric 0.14.0. Trend: flat (+0.0 from 61.4).

| Facet | Score |
|---|---|
| Discoverability | 81.5 |
| Contract Quality | 70.3 |
| Governance | 28.8 |
| Contract Governance | 28.8 |
| Operational Transparency | 63.2 |
| Developer Ergonomics | 54.8 |
| Commercial Clarity | 60.5 |
| Access Clarity | 60.5 |

Regulatory layer — **Insurance**: 33.3 (matched via tags).

## Agent readiness — 21.0 (agent-aware)

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

## Access

Enterprise · Self-serve signup — onboarding: self-serve, pricing: enterprise, trial: no (confidence: high).

## APIs (6)

- **Waxell Developer MCP Server** — Waxell Developer MCP is a hosted Model Context Protocol server that lets coding agents (Claude Code, Cursor, Windsurf, VS Code, Claude Desktop) query a Waxell instance in real t...
- **Waxell Cost Management API** — Model cost catalog and tenant-level overrides
- **Waxell Governance API** — Pre-execution policy checks and audit events
- **Waxell Prompts API** — Managed prompts retrievable by name and version
- **Waxell Runs API** — Lifecycle endpoints for agent execution runs
- **Waxell Telemetry API** — LLM calls, spans, steps, and quality scores recorded against a run

## Agentic access (1)

- **Waxell Agentic Access** — 12 operations · 10 acting · 2 human-in-the-loop

## Security (2)

- **Waxell Authentication** — apiKey/http · 2 schemes
- **Waxell Domain Security** — TLSv1.3 · HSTS

## Plans (1)

- **Waxell Plans Pricing**

## Use cases (6)

- **Govern Third-Party Coding Agents** — Enforce policies on Claude Code, Cursor, Windsurf, VS Code, and Claude Desktop without modifying their code.
- **Instrument Self-Built Agents** — Add full observability to LangChain, CrewAI, OpenAI Agents SDK, or custom Python agents with the @waxell.observe decorator.
- **Cost-Capped Agent Deployment** — Set budgets on token spend per agent, user, or tenant; block runs that exceed configured limits.
- **PII-Safe MCP Tool Use** — Scan MCP tool inputs/outputs for PII, credentials, and secrets with warn/block/redact responses.
- **Durable Long-Running Workflows** — Use the WorkflowEnvelope to checkpoint multi-step agent workflows so they can resume after interruption.
- **Compliance-Ready AI Operations** — Maintain SOC 2 Ready posture with immutable audit trails, encrypted PII, and EU data residency.

## Tags

AI Agent Governance, Observability, Policy Enforcement, LLM Telemetry, Cost Management, MCP, Agent Runtime

---

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