# AgenticEmail (remote · api.agenticemail.dev)

Hosted email for AI agents: create inboxes, send, receive, and reply over MCP with scoped API keys

- Trust score: 36/100 (low)
- Change this week: +14
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `api.agenticemail.dev`: 36/100 (this document), [markdown](https://verifymcp.io/servers/dev-agenticemail-mcp/api.md), [page](https://verifymcp.io/servers/dev-agenticemail-mcp/api)

## Channel facts

- Endpoint: `https://api.agenticemail.dev/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - The endpoint enforces authorisation, but returns a challenge with no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
- **Schema Quality & AI Usability**: 0/100
  - Schema blocked by authentication: the endpoint requires auth we don't have to read it.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Capabilities**: 0/100
  - Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add --transport http dev-agenticemail-mcp https://api.agenticemail.dev/mcp
```

### Codex

```toml
[mcp_servers.dev-agenticemail-mcp]
url = "https://api.agenticemail.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-agenticemail-mcp": {
      "type": "remote",
      "url": "https://api.agenticemail.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-agenticemail-mcp --url https://api.agenticemail.dev/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-agenticemail-mcp:
    url: "https://api.agenticemail.dev/mcp"
```

### Other

```json
{
  "mcpServers": {
    "dev-agenticemail-mcp": {
      "type": "http",
      "url": "https://api.agenticemail.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-01 (score 36, 0)

- [security regression] Endpoint reachability: reachable → behind authorisation

### 2026-07-31 (score 36, +14)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 22, −36)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 58, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-07-28 (score 57, +35)

- [security regression] Authorization: fail → unverified
- [security improvement] Transport: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 0
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: good
- [functional] First check of Schema quality: pass

### 2026-07-27 (score 22, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 22)

First indexed and scored.

## MCP tools (9)

### `create_inbox` (~57 tokens)

Create a new inbox. Omit username for a random one; omit domain to use the default (or only verified) domain.

Input parameters:

- `display_name` (string)
- `domain` (string)
- `username` (string)

### `list_inboxes` (~17 tokens)

List all inboxes in the account.

### `list_threads` (~26 tokens)

List conversation threads, optionally scoped to an inbox.

Input parameters:

- `inbox_id` (string)

### `get_thread` (~24 tokens)

Get a thread with all its messages.

Input parameters:

- `thread_id` (string, required)

### `list_messages` (~23 tokens)

List recent messages in an inbox.

Input parameters:

- `inbox_id` (string, required)

### `get_message` (~43 tokens)

Get a single message by id, including attachment metadata. Use read_attachment to read attachment contents.

Input parameters:

- `inbox_id` (string, required)
- `message_id` (string, required)

### `read_attachment` (~86 tokens)

Read an attachment as structured content: PDFs are converted to markdown (scanned pages are flagged via pages_needing_ocr), text attachments are returned as-is. Binary types (images, archives, office docs) are not supported - download those via the REST attachment endpoint.

Input parameters:

- `attachment_id` (string, required)
- `inbox_id` (string, required)
- `message_id` (string, required)

### `send_message` (~52 tokens)

Send a new email from an inbox.

Input parameters:

- `html` (string)
- `inbox_id` (string, required)
- `subject` (string, required)
- `text` (string)
- `to` (array, required)

### `reply_to_message` (~46 tokens)

Reply to a message; recipients, subject and threading are set automatically.

Input parameters:

- `inbox_id` (string, required)
- `message_id` (string, required)
- `text` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-agenticemail-mcp/api#diagnostics

## Score history

- 2026-08-03: 36
- 2026-08-02: 36
- 2026-08-01: 36
- 2026-07-31: 36
- 2026-07-30: 22
- 2026-07-29: 58
- 2026-07-28: 57
- 2026-07-27: 22
- 2026-07-26: 22

## Links

- Remote endpoint: https://api.agenticemail.dev/mcp
- Authorisation metadata: https://api.agenticemail.dev/.well-known/oauth-protected-resource/mcp
- Website: https://agenticemail.dev/docs/mcp
- Changelog RSS feed: https://verifymcp.io/servers/dev-agenticemail-mcp/api/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-agenticemail-mcp/api/changelog.json
- HTML version of this page: https://verifymcp.io/servers/dev-agenticemail-mcp/api