# em[ai]l

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

eml.ai provides a filtered email service for AI agents, allowing them to read forwarded messages without accessing the full inbox. The platform forwards selected emails to private aliases and connects them to AI agents over MCP, ensuring privacy and control. Users can choose which messages to share, with plans ranging from free trial to paid tiers.

## Kin Score — 14.6 / 100 (emerging)

Scored 2026-11-13 under rubric 0.28.0.

| Facet | Score |
|---|---|
| Discoverability | 57.1 |
| Contract Quality | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 14.3 |
| Developer Ergonomics | 9.5 |
| Access Clarity | 27.7 |

Regulatory layer — **Horizontal (data, software, accessibility, platform)**: 12.7 (matched via fallback).

## Agent readiness — 3.1 (human-only)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | documented |
| Auth Clarity | no |
| 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 | no |
| Protected Resource Metadata | no |
| Dynamic Client Registration | no |
| 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)

- **eml.ai API** — Filtered email service API for AI agents, providing endpoints to manage addresses, forward email, and interact via MCP.

## Security (1)

- **em[ai]l Domain Security** — TLSv1.3 · DMARC

## Tags

Email, Artificial Intelligence, Privacy, Filtering, Software-as-a-Service

---

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