agentsclimarketplace

Purpletoadmail skill

Skill hixistudio/purpletoadmail-skill

Agent skill for using PurpleToad Mail

Install
npx -y skills add hixistudio/purpletoadmail-skill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

A guide for using PurpleToad Mail with AI agents. Use whenever the user wants to send, receive, search, schedule, or manage email, set up domains/mailboxes/aliases, configure the PurpleToad Mail MCP server, troubleshoot deliverability issues, or integrate email into an app or workflow. Covers installation, authentication, tool selection, common workflows, and guardrails.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

8.5 KB, ~2.1k tokens by cl100k_base, as published. Nobody here has run it

PurpleToad Mail Skill

When to use this skill

  • The user wants to send, receive, search, schedule, or track email.
  • The user wants to add a domain, create a mailbox, or set up an alias.
  • The user wants to install or configure the PurpleToad Mail MCP server.
  • The user is troubleshooting email delivery, DNS, or API errors.
  • The user is building an app or automation that uses PurpleToad Mail.

What is PurpleToad Mail?

PurpleToad Mail is a programmable email platform. You bring your own domains, create mailboxes and aliases, and send/receive email through an API and an MCP server. The MCP server lets any compatible AI agent call PurpleToad Mail tools natively.

Installation

  1. Clone and build the MCP server:
git clone https://github.com/hixistudio/purpletoadmail-mcp.git
cd purpletoadmail-mcp
npm install
npm run build
  1. Get an API key from the dashboard at https://app.purpletoadmail.com → Settings → API Keys. Keys start with pt_live_ or pt_test_.

  2. Configure the server. Choose one method:

Environment variables:

export PURPLETOAD_API_KEY="pt_live_your_key_here"
export PURPLETOAD_DEFAULT_FROM="[email protected]"

Config file:

mkdir -p ~/.purpletoad
cat > ~/.purpletoad/config.json <<EOF
{
  "apiKey": "pt_live_your_key_here",
  "defaultFrom": "[email protected]"
}
EOF
  1. Add the MCP server to your AI client:

Claude Desktop:

{
  "mcpServers": {
    "purpletoad": {
      "command": "npx",
      "args": ["-y", "purpletoadmail-mcp"],
      "env": {
        "PURPLETOAD_API_KEY": "pt_live_your_key_here",
        "PURPLETOAD_DEFAULT_FROM": "[email protected]"
      }
    }
  }
}

Kimi Code:

{
  "mcpServers": {
    "purpletoad": {
      "command": "npx",
      "args": ["-y", "purpletoadmail-mcp"],
      "env": {
        "PURPLETOAD_API_KEY": "pt_live_your_key_here",
        "PURPLETOAD_DEFAULT_FROM": "[email protected]"
      }
    }
  }
}

Cursor / Windsurf:

{
  "mcpServers": {
    "purpletoad": {
      "command": "npx",
      "args": ["-y", "purpletoadmail-mcp"],
      "env": {
        "PURPLETOAD_API_KEY": "pt_live_your_key_here"
      }
    }
  }
}

If you are running from the local repo instead of npm, replace purpletoadmail-mcp with the path to the built repo.

Tool reference

Use these tools when helping the user. Always prefer tool calls over explaining how to use the API.

Account

  • get_account — Show account profile, plan, and usage stats. Use when the user asks about limits, quota, or subscription.

Sending email

  • send_email — Send an email from a PurpleToad Mail mailbox.
  • schedule_email — Schedule a future email.
  • cancel_scheduled_email — Cancel a scheduled email before it sends.
  • list_outbound_messages — List sent emails with delivery status.
  • get_outbound_message — Get detailed delivery history for one sent email.

Receiving email

  • list_messages — List inbound emails with filters (unread, since, from, thread).
  • get_message — Get full message body and attachments.
  • search_messages — Full-text search across inbound email.
  • mark_read — Mark a message as read.
  • archive_message — Archive a message.

Domains and infrastructure

  • list_domains — List domains with verification status and mailbox counts.
  • get_domain — Show DNS records and verification details for one domain.
  • create_domain — Add a new domain and return DNS records to copy-paste. Requires manage scope.
  • list_mailboxes — List mailboxes with quota usage.
  • get_mailbox — Show mailbox details.
  • create_mailbox — Create a mailbox. Returns a one-time password. Requires manage scope.
  • update_mailbox_password — Change a mailbox password. Requires manage scope.
  • list_aliases — List aliases and their targets.
  • create_alias — Create an alias that forwards to one or more mailboxes. Requires manage scope.

Common workflows

Send a simple email

  1. If from is not provided, call get_account or list_mailboxes to confirm the default sender is valid.
  2. Call send_email with from, to, subject, and either text or html.
  3. Return the message_id and any rate-limit info to the user.

Example:

send_email(
  from="[email protected]",
  to=["[email protected]"],
  subject="Welcome!",
  text="Thanks for signing up."
)

Check unread emails

  1. Call list_messages(mailbox="[email protected]", unread_only=true).
  2. For the most relevant message, call get_message(message_id=...) .
  3. If the user wants to reply, call send_email with a thread_id if available.

Search for an email

  1. Call search_messages(query="invoice Acme").
  2. Ask the user which result, or call get_message on the top match.

Add a new domain

  1. Call create_domain(domain="mycompany.com").
  2. Format the returned DNS records as a table (MX, SPF, DKIM, DMARC).
  3. Tell the user to paste them into their DNS provider.
  4. After the user confirms, call get_domain(domain="mycompany.com") to check verification status.

Create a mailbox

  1. Call create_mailbox(domain_id="...", local_part="support", display_name="Support", quota_mb=512).
  2. Show the generated password once and tell the user to change it immediately.

Create an alias

  1. Call create_alias(domain_id="...", source="support", targets=["[email protected]", "[email protected]"]).
  2. Confirm the alias and its targets.

Schedule a follow-up

  1. Call schedule_email(..., send_at="2026-06-08T09:00:00Z").
  2. Return the scheduled message ID and send time.

Track delivery

  1. Call list_outbound_messages(date_from="...", status="delivered").
  2. For any interesting message, call get_outbound_message(message_id=...).

Configuration options

VariableRequiredDefaultDescription
PURPLETOAD_API_KEYYesAPI key (pt_live_* or pt_test_*)
PURPLETOAD_DEFAULT_FROMNoDefault sender address
PURPLETOAD_BASE_URLNohttps://api.purpletoadmail.comAPI base URL
PURPLETOAD_TIMEOUTNo30Request timeout (seconds)
PURPLETOAD_TRANSPORTNostdiostdio or sse
PURPLETOAD_PORTNo3001Port for SSE transport

Guardrails and troubleshooting

Before sending

  • The from address must be a real mailbox owned by the account, not an alias.
  • Use list_mailboxes if you are unsure which addresses are valid.
  • If from is omitted, PURPLETOAD_DEFAULT_FROM must be set.

Deliverability checklist

If an email bounces or lands in spam:

  1. Call get_domain for the sender domain and confirm all DNS records are published: MX, SPF, DKIM, DMARC.
  2. Verify the DKIM public key in DNS matches the value returned by get_domain.
  3. Check the sender reputation with list_outbound_messages and get_outbound_message.
  4. Ask the user to confirm the receiving domain is not suppressing the address.
  5. For attachment failures, ensure the attachment size is within the plan limit and the content is not flagged by the recipient provider.

Common errors

  • INVALID_FROM — Use list_mailboxes to pick a valid sender.
  • DOMAIN_NOT_VERIFIED / DOMAIN_NOT_ACTIVE — DNS records are missing or wrong. Use get_domain to see the required records.
  • RATE_LIMIT_EXCEEDED — Plan quota reached. Suggest waiting or upgrading.
  • INSUFFICIENT_SCOPE — The API key lacks permission. Create a key with the required scope (send, read, manage).
  • NO_DEFAULT_FROM — Provide from in the tool call or set PURPLETOAD_DEFAULT_FROM.

Security notes

  • API keys are shown once in the dashboard. If lost, revoke and create a new one.
  • Do not commit API keys to Git.
  • The SSE transport requires Authorization: Bearer <PURPLETOAD_API_KEY> on the initial /sse request.
  • Mailbox passwords are shown once. Tell the user to change them immediately.

What ships with it: 2 files

1.8 KB alongside SKILL.md

Gives 0 of the 12 instructions most mcp tooling skills give in ~2.1k tokens

Counted across 638 of the 750 authors here whose files we hold, read 2026-08-07

  • Create ten complex or independent read-only evaluation questionsin 69 of 638, across 15 files
  • Test servers using MCP Inspectorin 61 of 638, across 19 files
  • Provide actionable error messages with specific next stepsin 54 of 638, across 12 files
  • Prioritize comprehensive API coverage over specific workflows or workflow toolsin 54 of 638, across 12 files
  • Use TypeScript and Streamable HTTP for remote servers or clientsin 54 of 638, across 8 files
  • Define structured output schemas where possiblein 50 of 638, across 8 files
  • Use Zod or Pydantic for input schemasin 47 of 638, across 5 files
  • Fetch MCP specification pages with markdown suffixin 46 of 638, across 4 files
  • Load framework documentation using WebFetchin 45 of 638, across 3 files
  • Verify each evaluation answer independentlyin 45 of 638, across 3 files
  • Implement API client with authentication and paginationin 45 of 638, across 3 files
  • Define input schemas with validationin 27 of 638, across 9 files

Said here and by no other author read

  • prefer tool calls over explaining api usage
  • verify default sender before sending email
  • return message id and rate limit info
  • reply using thread id if available
  • format requested dns records as a table
  • instruct user to change generated password immediately

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.