Use Warmerly with AI (MCP)
Warmerly runs a Model Context Protocol server, so an AI assistant you already use — Claude, ChatGPT, Claude Code, Cursor, or any other MCP client — can look things up in your Warmerly workspace directly: your mailboxes and their health, campaigns, leads, inbox conversations, deliverability checks and transactional email, all without you copy-pasting data back and forth. You sign in once with your normal Warmerly login; after that the assistant asks Warmerly, not you.
Available on every plan, including Free. There's no separate API key or add-on required to connect — just your Warmerly account.
Server URL
https://app.warmerly.com/api/mcp
Every client below connects to this one URL.
Connect
claude.ai
- Go to Settings → Connectors → Add custom connector.
- Paste
https://app.warmerly.com/api/mcpas the server URL. - Sign in with your Warmerly account when prompted.
ChatGPT
- Go to Settings → Connectors, and turn on Advanced (or Developer mode) if you don't already see an option to add an MCP server.
- Add a new MCP server and paste
https://app.warmerly.com/api/mcpas the URL. - Sign in with your Warmerly account when prompted.
Connector availability depends on your ChatGPT plan — if you don't see the option, it isn't enabled on your current plan.
Claude Code
claude mcp add --transport http warmerly https://app.warmerly.com/api/mcp
Then run /mcp inside Claude Code and follow the prompt to sign in with your Warmerly account.
Cursor
Add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"warmerly": {
"url": "https://app.warmerly.com/api/mcp"
}
}
}
Cursor will prompt you to sign in with your Warmerly account the first time it calls a tool.
Claude plugin and skills
The connection gives an assistant Warmerly's tools; skills teach it how to use them well. Warmerly publishes four, each a workflow rather than a list of tools:
- launch-outreach-campaign: from your ideal customer to a verified lead list, a sequence that follows cold-email best practice, a readiness check and a launch.
- deliverability-doctor: why mail lands in spam or bounces (mailbox health, SPF, DKIM, DMARC, MX, blocklists, placement tests) and exactly what to fix.
- reply-triage: separate real replies from autoresponders and unsubscribes, draft answers, and suppress anyone who asked to be left alone.
- transactional-email-setup: verify a sending domain for app email and check delivery.
Every skill asks before bulk sends, launches or replies unless you tell it it may act on its own, and your plan limits and suppression list apply exactly as in the dashboard.
The plugin and the skill downloads are being published now. Until the links appear on this page, connecting with the steps above gives you every tool; the skills only add the workflows.
Claude Code installs the server and all four skills as one plugin:
/plugin marketplace add <the Warmerly plugin repo>
/plugin install warmerly@warmerly
Then run /mcp and sign in. (Already connected with claude mcp add? The plugin adds the same
server, so you can remove the manual one.)
claude.ai: add the connector as above, then upload each skill's .zip under
Settings → Capabilities → Skills.
What happens when you sign in
Signing in opens the normal Warmerly login (or lets you use an existing session), then a consent screen where you choose one workspace for that connection. Every tool call from that assistant is scoped to the workspace you picked — it can't see or touch your other workspaces. If you need the assistant to work in a different workspace, connect again and pick that one; each connection is independent.
Tools
Phase 1 is read-only: agents can look but not send or launch yet.
| Tool | What it does |
|---|---|
search_docs | Search the Warmerly documentation for pages relevant to a question. |
read_doc | Read the full content of a Warmerly docs page by slug. |
get_account_overview | Snapshot of the workspace: plan, quota usage, mailbox/campaign counts, setup gaps. |
get_connect_mailbox_link | Get the URL to connect a mailbox yourself (mailbox credentials never pass through an MCP client). |
list_mailboxes | List the workspace's connected mailboxes, their status and health. |
get_mailbox_health | A mailbox's daily health history plus its latest SPF/DKIM/DMARC/MX check. |
check_domain | Run a live SPF/DKIM/DMARC/MX check against any domain. |
list_sending_domains | List the workspace's transactional email sending domains and verification status. |
list_transactional_emails | List recent transactional emails, newest first. |
get_transactional_email | Get one transactional email and its delivery event timeline. |
search_leads | Search Warmerly's lead database with a natural-language query or structured filters. |
count_leads | Count how many leads match a search, without fetching rows. |
list_campaigns | List the workspace's campaigns with status and send/reply counts. |
get_campaign | Get one campaign's settings, sequence steps and readiness to start. |
list_conversations | List inbox conversations (email/LinkedIn/WhatsApp), newest activity first. |
get_conversation | Get one conversation's message timeline and any draft reply. |
Privacy & safety
- Revocable any time. Every connection shows up under Settings → Connected apps, where you can revoke it — the assistant loses access immediately.
- Rate limited. 60 tool calls per minute per connection, so a runaway assistant can't hammer your account.
- Scoped to the workspace you chose. A connection can only ever see the one workspace you picked at sign-in, never your other workspaces.
- No passwords ever pass through the AI. Connecting a mailbox, or anything else that needs a password or OAuth grant, always happens in the Warmerly dashboard itself — the assistant can at most hand you a link to open.
Troubleshooting
- The assistant says it got a 401 / lost access. The connection was revoked or its token expired — reconnect using the steps above.
- The assistant is looking at the wrong workspace. Each connection is pinned to one workspace. Reconnect and pick the other workspace at the consent screen; you can keep both connections if you use both workspaces from AI.
