# io.github.mrfentmen/mandrill-mcp (npm · mandrill-mcp)

MCP server for Mandrill: transactional email MCP: real tools for real work.

- Trust score: 68/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `mandrill-mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/mrfentmen-mandrill-mcp/mandrill-mcp.md), [page](https://verifymcp.io/servers/mrfentmen-mandrill-mcp/mandrill-mcp)

## Channel facts

- Registry: `npm`
- Package: `mandrill-mcp`
- Version: `1.0.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-11-21.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 31 of 93 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 19 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1438 tokens (~41/item across 35 items; 35 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 8 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_email" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 35 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.mrfentmen/mandrill-mcp server?

io.github.mrfentmen/mandrill-mcp runs locally as an npm package, launched with npx -y mandrill-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add mrfentmen-mandrill-mcp -- npx -y mandrill-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "mrfentmen-mandrill-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mandrill-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mrfentmen-mandrill-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mandrill-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add mrfentmen-mandrill-mcp -- npx -y mandrill-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mrfentmen-mandrill-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mandrill-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mrfentmen-mandrill-mcp --command npx --arg -y --arg mandrill-mcp
```

### Hermes

```yaml
mcp_servers:
  mrfentmen-mandrill-mcp:
    command: "npx"
    args: ["-y", "mandrill-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "mrfentmen-mandrill-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "mandrill-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add mrfentmen-mandrill-mcp -t stdio -c npx -a -y mandrill-mcp
```

### Other

```json
{
  "mcpServers": {
    "mrfentmen-mandrill-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mandrill-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-11-21 (score 68, +6)

- [functional improvement] Stability: unverified → 0.43

### 2026-11-10 (score 62, +5)

- [security improvement] Source repository: unverified → pass

### 2026-11-09 (score 57, +10)

- [security regression] Provenance: pass → unverified
- [security improvement] Malware scan: unverified → pass

### 2026-11-08 (score 47)

First indexed and scored.

## MCP tools (35)

### `send_email` (~134 tokens)

Send a transactional email through Mandrill. This sends real mail from a verified domain.

Input parameters:

- `from_email` (string, required): Verified sending address
- `from_name` (string): Sender display name
- `html` (string): HTML body
- `important` (boolean): Mark the message as important
- `subject` (string, required): Subject line
- `tags` (array): Tags for reporting
- `text` (string): Plain-text body (auto-generated when omitted)
- `to` (array, required): Recipients
- `track_clicks` (boolean): Track clicks
- `track_opens` (boolean): Track opens

### `send_template_email` (~122 tokens)

Send an email rendered from a stored Mandrill template.

Input parameters:

- `from_email` (string, required): Verified sending address
- `from_name` (string): Sender display name
- `merge_vars` (array): Per-recipient merge vars: [{rcpt: 'a@b.c', vars: [{name, content}]}]
- `subject` (string): Override the template subject
- `template_content` (array): Handlebars replacements: [{name, content}]
- `template_name` (string, required): Template slug
- `to` (array, required): Recipients

### `send_raw_email` (~74 tokens)

Send a pre-built MIME message through Mandrill.

Input parameters:

- `from_email` (string, required): Verified sending address
- `from_name` (string): Sender display name
- `raw_message` (string, required): Full MIME message, including headers
- `subject` (string): Subject override
- `to` (array, required): Recipient addresses

### `search_messages` (~83 tokens)

Search sent messages by Mandrill's search syntax, e.g. 'email:someone@example.com'.

Input parameters:

- `date_from` (string): ISO 8601 start date
- `date_to` (string): ISO 8601 end date
- `limit` (integer): Max results, Mandrill defaults to 100
- `query` (string, required): Search query

### `get_message_info` (~33 tokens)

Get delivery details and open/click counts for one message.

Input parameters:

- `id` (string, required): Mandrill message id

### `get_message_content` (~31 tokens)

Get the stored HTML body of a sent message.

Input parameters:

- `id` (string, required): Mandrill message id

### `list_scheduled_messages` (~32 tokens)

List messages that are scheduled but not sent yet.

Input parameters:

- `to` (string): Only messages to this address

### `cancel_scheduled_message` (~37 tokens)

Cancel a scheduled message. Destructive: the message will not be sent.

Input parameters:

- `id` (string, required): Mandrill message id

### `reschedule_message` (~49 tokens)

Move a scheduled message to a new send time.

Input parameters:

- `id` (string, required): Mandrill message id
- `send_at` (string, required): New send time, ISO 8601 with timezone

### `parse_email` (~37 tokens)

Parse a raw MIME message and return Mandrill's extracted headers, body and attachments.

Input parameters:

- `raw_message` (string, required): Full MIME message

### `add_template` (~82 tokens)

Create a Mandrill template from Handlebars code.

Input parameters:

- `code` (string, required): Handlebars template source
- `from_email` (string): Default sender address
- `from_name` (string): Default sender name
- `name` (string, required): Template name
- `subject` (string): Default subject
- `text` (string): Plain-text part

### `list_templates` (~15 tokens)

List every template in the account.

### `get_template` (~23 tokens)

Get one template by name.

Input parameters:

- `name` (string, required): Template name

### `update_template` (~81 tokens)

Update a template's code, subject or sender defaults.

Input parameters:

- `code` (string): New Handlebars source
- `from_email` (string): Default sender address
- `from_name` (string): Default sender name
- `name` (string, required): Template name
- `subject` (string): Default subject
- `text` (string): Plain-text part

### `delete_template` (~26 tokens)

Delete a template. Destructive and permanent.

Input parameters:

- `name` (string, required): Template name

### `render_template` (~60 tokens)

Render a template with merge vars without sending anything.

Input parameters:

- `merge_vars` (array): Merge vars: [{name, content}]
- `template_content` (array): Handlebars replacements: [{name, content}]
- `template_name` (string, required): Template name

### `publish_template` (~41 tokens)

Publish a template so it can be sent by name.

Input parameters:

- `code` (string): Optional code to publish with it
- `name` (string, required): Template name

### `ping` (~21 tokens)

Check that the API key works. Returns PONG when it does.

### `get_user_info` (~18 tokens)

Read the account's reputation and sending quota.

### `list_senders` (~20 tokens)

List the domains and addresses this account has sent from.

### `list_tags` (~19 tokens)

List tags with their send, open and click totals.

### `delete_tag` (~28 tokens)

Delete a tag and its reporting history. Destructive.

Input parameters:

- `tag` (string, required): Tag name

### `list_rejects` (~35 tokens)

List addresses Mandrill has rejected, with the reason.

Input parameters:

- `include_expired` (boolean): Include expired rejections

### `delete_reject` (~33 tokens)

Remove one address from the rejection list so it can be mailed again.

Input parameters:

- `email` (string, required): Address to unblock

### `list_webhooks` (~17 tokens)

List webhook targets and their delivery counters.

### `add_webhook` (~66 tokens)

Create a webhook that posts Mandrill events to a URL.

Input parameters:

- `description` (string): Human label
- `events` (array): Event names, e.g. ['send', 'open', 'hard_bounce']
- `url` (string, required): HTTPS endpoint to receive events

### `delete_webhook` (~31 tokens)

Delete a webhook. Destructive: events stop being delivered.

Input parameters:

- `id` (integer, required): Webhook id

### `list_inbound_domains` (~18 tokens)

List domains configured to receive inbound mail.

### `list_inbound_routes` (~31 tokens)

List inbound routing rules, optionally for one domain.

Input parameters:

- `domain` (string): Limit to this domain

### `add_inbound_domain` (~30 tokens)

Register a domain for inbound mail processing.

Input parameters:

- `domain` (string, required): Domain to receive mail for

### `list_subaccounts` (~17 tokens)

List subaccounts with reputation and status.

### `add_subaccount` (~48 tokens)

Create a subaccount for separate sending reputation.

Input parameters:

- `id` (string, required): Unique subaccount id
- `name` (string): Display name
- `notes` (string): Free-form notes

### `list_urls` (~16 tokens)

List tracked URLs and their click totals.

### `list_exports` (~13 tokens)

List activity export jobs.

### `list_metadata` (~17 tokens)

List custom metadata fields defined on the account.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/mrfentmen-mandrill-mcp/mandrill-mcp#diagnostics

## Score history

- 2026-11-21: 68
- 2026-11-20: 62
- 2026-11-19: 62
- 2026-11-18: 62
- 2026-11-17: 62
- 2026-11-16: 62
- 2026-11-15: 62
- 2026-11-14: 62
- 2026-11-13: 62
- 2026-11-12: 62
- 2026-11-11: 62
- 2026-11-10: 62
- 2026-11-09: 57
- 2026-11-08: 47

## Common questions

### What is the io.github.mrfentmen/mandrill-mcp server?

io.github.mrfentmen/mandrill-mcp is listed in the public MCP registry as io.github.mrfentmen/mandrill-mcp. MCP server for Mandrill: transactional email MCP: real tools for real work. This page covers its npm package (mandrill-mcp).

### Is the io.github.mrfentmen/mandrill-mcp server safe to use?

io.github.mrfentmen/mandrill-mcp scores 68 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.mrfentmen/mandrill-mcp server expose?

io.github.mrfentmen/mandrill-mcp exposes 35 tools: send_email, send_template_email, send_raw_email, search_messages, get_message_info, and 30 more. Their descriptions and schemas cost roughly 1,438 tokens of context every time the server is loaded.

### Is the io.github.mrfentmen/mandrill-mcp server still maintained?

io.github.mrfentmen/mandrill-mcp is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.mrfentmen/mandrill-mcp server under?

io.github.mrfentmen/mandrill-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the io.github.mrfentmen/mandrill-mcp server?

VerifyMCP ran 16 checks on io.github.mrfentmen/mandrill-mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/mandrill-mcp
- Socket report: https://socket.dev/npm/package/mandrill-mcp
- Repository: https://github.com/mrfentmen/awesome-servers
- Changelog RSS feed: https://verifymcp.io/servers/mrfentmen-mandrill-mcp/mandrill-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/mrfentmen-mandrill-mcp/mandrill-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/mrfentmen-mandrill-mcp/mandrill-mcp.json
- HTML version of this page: https://verifymcp.io/servers/mrfentmen-mandrill-mcp/mandrill-mcp
