# Étincel

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

Étincel is a remote MCP server that gives Claude a trained writing voice. Connect it from Claude Code or Claude Desktop, then ask for an email, a Slack message, a PR review, or a blog post in your voice. Pick a premade tone or train one from your own samples, and audit any draft for AI-writing tells before you publish.

## Kin Score — 23.9 / 100 (emerging)

Scored 2026-11-13 under rubric 0.28.0.

| Facet | Score |
|---|---|
| Discoverability | 56.7 |
| Contract Quality | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 4.8 |
| Developer Ergonomics | 40.5 |
| Access Clarity | 42.6 |

Regulatory layer — **Horizontal (data, software, accessibility, platform)**: 21.8 (matched via fallback).

## Agent readiness — 19.6 (agent-aware)

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

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

## APIs (1)

- **Étincel MCP** — Remote MCP server providing Claude with a trained writing voice.

## MCP servers (1)

- **Étincel MCP Server**

## Security (2)

- **Étincel Authentication** — 1 scheme
- **Étincel Domain Security** — TLSv1.3 · HSTS

## Tags

Artificial Intelligence, MCP, Writing, Voice, Claude

---

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