Skip to main content
Glama
Email Sending MCP

Email Sending MCP

by resend

Enable Forge

enable-forge

Move a domain's sending to Forge and get the Forge CNAME plus any pending Receiving MX record to add at your DNS provider before verification.

Instructions

Enable Forge for a domain in Resend. Forge is Resend's own sending infrastructure, and enabling it starts moving the domain's sending onto Forge with a dedicated return path. Forge offers better deliverability and faster sending. Returns the domain with a new Forge CNAME record among its DNS records. For a domain that receives email, enabling also moves receiving, and the response includes a pending Receiving MX record with a new value. The whole flow is: 1. call this tool, 2. display the returned Forge CNAME record, and the pending Receiving MX record when there is one, to the user so they can update their DNS provider, 3. once the user has updated DNS, call verify-domain with scope ["forge"], 4. poll get-domain until the Forge CNAME record's status is "verified", matching it by name and value, and until the Receiving MX record is "verified" too when it moved. Do not rely on the top-level domain status for this: it can show "verified" before the MX record moves. Always pass scope ["forge"] when verifying Forge: it checks only the Forge record, so the records that are already verified are not re-proven. Enabling does not start verification, and the domain keeps sending through its current records while the Forge record verifies, so there is no interruption. Idempotent: calling it again for a domain already on Forge returns the current state without starting a new migration.

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": {
      "id": "<id>"
    },
    "name": "enable-forge"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesDomain ID
customReturnPathNoSubdomain for the Forge Return-Path address. Must start with a letter, end with a letter or digit, contain only letters, digits, and hyphens, and be 2 to 63 characters long. When omitted, Resend picks a label that is free in your DNS. Set once when Forge is enabled and cannot be changed afterwards.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.29.0

TDQS

A4.7/5.0
Behavior5/5

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

No annotations are supplied, so the description carries the full burden and does so: it discloses that enabling does not start verification, that the domain keeps sending through existing records during the transition, that receiving moves too when applicable, and that repeat calls are idempotent with no new migration. It also scopes verify-domain to ["forge"] to avoid re-proving already-verified records.

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-loaded with the purpose, then the numbered flow, which is the right structure for a multi-step operation. Slightly long with some restatement (the ["forge"] scope rationale is given twice, and "there is no interruption" is echoed), but nearly every sentence carries actionable detail.

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

Completeness4/5

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

With no output schema, the description usefully describes what is returned (the domain with a Forge CNAME record and optional pending Receiving MX record) and how to interpret it against DNS status. What remains underspecified is failure behavior, e.g. what a domain not yet eligible for Forge returns, but the operational loop an agent needs is fully covered.

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 id and customReturnPath semantics are already documented, including the set-once constraint and the auto-pick behavior when omitted. The description adds context about which records the call produces but nothing extra about the parameters themselves, so it sits near the baseline rather than above it.

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 ("Enable Forge for a domain in Resend") and immediately explains what Forge is and what the field-level effect is: a new Forge CNAME record plus, for receiving domains, a pending Receiving MX record. An agent knows this is distinct from get-domain or verify-domain 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 an explicit numbered end-to-end flow: call this tool, surface the returned CNAME/MX records to the user, then call verify-domain with scope ["forge"], then poll get-domain matching by name and value. It also states a when-not rule (do not rely on the top-level domain status) and an idempotency condition for repeat calls.

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

Deploy Server

Other Tools