Skip to main content
Glama
Cresca MCP Server

Cresca MCP Server

Send email (sends real email)

send_email
Destructive

Sends transactional email through Cresca with HTML/text or templates, optional attachments and scheduling, using an idempotency key to prevent duplicate sends.

Instructions

WARNING: this SENDS REAL EMAIL to real recipients through Cresca and cannot be undone (only a scheduled or still-queued email can be canceled). Confirm the recipients, sender and content with the user before calling it. Each recipient counts toward the plan's monthly email allowance.

POST /emails. Sends one transactional email to up to 50 recipients (to + cc + bcc), with html/text or a published template, optional attachments, tags, custom headers and scheduling up to 30 days ahead.

Works with sending-access and full-access API keys. The from address must be an active sender on a verified domain. Recipients on the suppression list are skipped and the call still succeeds.

idempotency_key is required: build it from the event ("order-confirmation/1042") and reuse it on every retry. If the result says already_sent, the email went out earlier: the task is done, do not retry with a new key. Returns { id }; check delivery with get_email.

Use it for transactional email (password resets, receipts, alerts), not newsletters or promotions: those belong in Cresca campaigns.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "to": "<to>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "send_email"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccNoCarbon-copy recipients.
toYesRecipient address or array of addresses. Up to 50 recipients in total across to, cc and bcc.
bccNoBlind carbon-copy recipients; never shown in headers.
fromNoSender, as "hello@acme.com" or "Acme <hello@acme.com>". Must be an active sender on a verified domain in the Cresca account. Required unless the template has a default sender.
htmlNoHTML body. Provide html, text or a template.
tagsNoUp to 10 { name, value } labels, e.g. { "name": "category", "value": "password_reset" }. ASCII letters, numbers, underscores and dashes, up to 256 characters. Tag names must be unique within the email.
textNoPlain-text body. If omitted, Cresca generates it from html. An empty string leaves the text part out.
headersNoCustom headers such as List-Unsubscribe or X-Entity-Ref-ID, up to 50. Headers Cresca controls (From, To, Cc, Bcc, Subject, Reply-To, Sender, Return-Path, Message-ID, Date, Content-Type and similar) are rejected; use the request fields instead.
subjectNoSingle line, up to 998 characters. Required unless the template has a default subject.
reply_toNoReply-To address(es). Defaults to the template's, else the sender's Reply-To.
templateNoSend a PUBLISHED template instead of html/text. Cannot be combined with html or text. subject, from and reply_to default to the template's values when omitted.
attachmentsNoUp to 20 files, 7 MB in total, as base64 content. Attaching by URL/path is not supported.
scheduled_atNoISO 8601 date-time to send at, up to 30 days ahead, e.g. "2026-10-21T09:00:00Z". A time in the past sends immediately. A scheduled email can be rescheduled or canceled until it is sent.
idempotency_keyYesRequired. 1 to 256 characters, built from the real-world event this email is about, e.g. "order-confirmation/1042" or "password-reset/<reset request id>". Use the SAME key every time you retry or redo this email (after an error, a timeout or a restart) and a NEW key only for a genuinely new email. Never use a random value or the time. Within 24 hours a repeated key returns the first result instead of sending again.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Goes well beyond the annotations: irreversibility and the narrow cancel window, monthly allowance consumption, suppression-list recipients being silently skipped while the call still succeeds, verified-domain sender requirement, and the already_sent outcome. The only tension is that annotations declare idempotentHint=false while the description describes key-based deduplication within 24 hours; this is defensible (dedup is conditional on the key) but the description could have reconciled the two explicitly.

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

Conciseness4/5

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

Front-loads the destructive warning before any mechanics, then moves through endpoint, auth, idempotency and routing in short paragraphs. Dense but nearly every sentence carries decision-relevant information; the title's parenthetical and a few clauses restate the same warning twice.

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

Completeness5/5

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

For a 14-parameter, nested-object mutation with no output schema, the description covers the return value ({ id }), the verification path (get_email), the failure mode (already_sent), and the access/domain prerequisites. Nothing an agent needs to call it safely is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, and the description earns above that by explaining how to construct idempotency_key from the real-world event, that it must be reused on retries and never randomized, and that from/subject/reply_to fall back to template defaults. It adds operational meaning the schema's per-field text does not carry.

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?

States a specific verb and resource ("Sends one transactional email") plus the transport (POST /emails) and scope (up to 50 recipients across to+cc+bcc). It explicitly separates itself from campaigns and from the batch sibling by framing this as single transactional email, so an agent can pick it without opening 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 Guidelines5/5

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

Gives explicit when-to-use (password resets, receipts, alerts) and when-not (newsletters/promotions belong in Cresca campaigns), plus a follow-up route to get_email for delivery status. It also states the pre-call requirement to confirm recipients, sender and content with the user.

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