Skip to main content
Glama
maillog-dev

maillog-mcp

Official
by maillog-dev
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

@maillog/node-sdk

Node SDK and MCP server for the Maillog email API. Other languages: Python · Go · Ruby · PHP · Rust

Install

npm install @maillog/node-sdk

Related MCP server: Inbound Email MCP Server

Get a key without an account

curl -X POST https://api.maillog.nl/v1/keys/sandbox \
  -H "Content-Type: application/json" \
  -d '{"email":"you@example.com"}'

The key it returns may only send to that address and expires after 24 hours. For your own domains, sign up at https://maillog.nl/signup.

Send

import { Maillog } from "@maillog/node-sdk";

const maillog = new Maillog(process.env.MAILLOG_API_KEY);

const { id } = await maillog.emails.send({
  from: "Acme <noreply@acme.nl>",
  to: ["you@example.com"],
  subject: "hello",
  html: "<p>it works</p>",
});

emails.sendBatch(emails) takes 1 to 100 at a time. emails.list({ limit, offset, status }) returns what was sent, with delivery status and open/click counts.

Errors

Failures throw MaillogError with .status and .body, so a 422 from validation and a 403 from an expired key can be handled apart.

import { MaillogError } from "@maillog/node-sdk";

try {
  await maillog.emails.send(params);
} catch (err) {
  if (err instanceof MaillogError && err.status === 422) {
    // body carries errors[] with the offending field
  }
}

There is no retry logic, on purpose: a client that silently resends produces duplicate mail, and only you know whether that is acceptable.

MCP server

The package ships an MCP server so an assistant can send mail directly.

claude mcp add maillog --env MAILLOG_API_KEY=ma_xxx -- npx -y maillog-mcp

Tools: send_email, list_emails.

Options

new Maillog(apiKey, {
  baseUrl: "http://localhost:3086",  // default https://api.maillog.nl
  timeoutMs: 30_000,
});

Develop

npm run build          # tsc to dist/
node --test src/*.test.ts

MIT.

Available Tools

2 tools
list_emailsList sent emailsA

List emails previously sent through Maillog, newest first, with delivery status and open/click counts. Use this to check whether a message actually went out.

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNo
offsetNo
statusNoFilter, e.g. "sent", "queued", "failed"

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden. It adds behavioral details by specifying ordering ('newest first') and return fields ('delivery status and open/click counts'). However, it doesn't address pagination defaults, rate limits, or the meaning of status values.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences with the action front-loaded. Every clause adds information—resource, ordering, output, and use case—leaving no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the essential return contents and use case, but with no output schema and no annotations, it leaves some gaps around default limit, response format, and failure behavior. Adequate for a simple list but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only status has a schema description; limit and offset have none, and the description doesn't explain them. The schema coverage is 33%, below the 50% threshold, so the description needed to compensate and didn't.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear action ('List') and target resource ('emails previously sent through Maillog'), and it notes output contents ('delivery status and open/click counts'). This makes it easily distinguishable from its only sibling, send_email, which is a write operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'Use this to check whether a message actually went out' provides an explicit use case. It doesn't spell out exclusions or name send_email, but the context of listing vs sending makes the choice clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

send_emailSend an emailA

Send a transactional email through Maillog. The 'from' address must be on a domain verified in the Maillog dashboard, except for sandbox keys, which may only send to the address the sandbox key was issued for.

ParametersJSON Schema
NameRequiredDescriptionDefault
ccNo
toYesRecipient addresses
bccNo
fromYesSender, e.g. "Acme <noreply@acme.nl>"
htmlNoHTML body. Provide html or text.
textNoPlain text body. Provide html or text.
subjectYes
reply_toNo

TDQS

A3.7/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the disclosure burden. It adds a meaningful behavioral constraint: 'from' must be on a domain verified in Maillog, and sandbox keys may only send to the address the key was issued for. However, it does not disclose failure behavior, delivery semantics, or other side effects beyond the act of sending.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long: the first states the purpose, the second states the key constraint. There is no filler, and the most important information is front-loaded before the caveat.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter write operation with no annotations and no output schema, the description is minimally adequate: it gives the core purpose and one critical precondition. It omits response/error behavior, the need to supply html or text, and any guidance about selecting this tool over list_emails, leaving clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 50%; from, to, html, and text have schema descriptions, while cc, bcc, subject, and reply_to do not. The description adds important meaning to 'from' by requiring a verified domain and to 'to' through the sandbox restriction, but it does not compensate for the wholly undocumented remaining parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: 'Send a transactional email through Maillog.' The action 'Send' immediately distinguishes this tool from the read-oriented sibling list_emails, so an agent can tell them apart without inspecting the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not-to-use guidance. The phrase 'transactional email' implies the intended context, and the sibling list_emails is clearly a different operation, but no alternative or exclusion condition is named. Usage is only implied, not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updatesv0.1.0
    • First observedlist_emails
    • First observedsend_email
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0
Disambiguation5/5

send_email and list_emails are clearly distinct: one creates a new email, the other reads previously sent emails. There is no overlap or ambiguity between the two operations.

Naming Consistency5/5

Both tool names follow a consistent verb_noun snake_case pattern, matching the broader MCP convention. The style is predictable and uniform across the small set.

Tool Count3/5

Two tools is on the thin side for a server, but the pair covers the core send-and-verify workflow implied by the Maillog domain. It is functional yet minimal, so the count is borderline appropriate.

Completeness4/5

The server covers the essential email send and delivery-check lifecycle with no obvious dead ends. Minor gaps exist, such as no single-email detail lookup or domain management, but the core workflow is workable.

Maintenance

ActivityMaintained
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/maillog-dev/sdk-node'

If you have feedback or need assistance with the MCP directory API, please join our Discord server