AI Assistants for Cold Email: What Connects and How

Short answer: in September 2026 every major AI assistant can reach outside tools, through MCP servers, API actions or both. What differs is where the server has to run and how it authenticates. The hosted Outreach2day MCP server is live at https://public.outreach2day.com/mcp and signs in with OAuth (since 29 September 2026): you add the URL and sign in from the assistant, no API key. One command (curl -fsSL https://outreach2day.com/install | sh) adds it to Claude Code, Cursor, VS Code, Windsurf, Gemini CLI and Codex and prints the connector steps for Claude Desktop. claude.ai connectors, the ChatGPT app, grok.com and the Gemini app connect the same way; per their docs so do Mistral Le Chat and Microsoft Copilot Studio (OAuth with dynamic client registration), which we have not tested yet. The xAI API and n8n take an API key as a Bearer header per their docs, not tested by us yet. ChatGPT also works through a custom GPT with an Action on the REST API.

Checked September 2026. Each assistant's guide below cites the vendor documentation it was checked against.

Assistants at a Glance

"First available" is the vendor's own date for the feature where it publishes one. xAI does not publish a date for custom connectors on grok.com, and Google does not publish one for custom apps in the Gemini app.

Assistants by Task

Four jobs come up in every cold email setup. What an assistant can do with each today, over the Outreach2day API:

By assistant, the practical split:

Pick and connect an AI assistant, step by step

1. Start from where you work. If your leads and copy live in a repo, pick the coding agent you already use; if they live in chat, pick ChatGPT or Claude; if the job is a daily report, pick n8n

2. Add the server and sign in. Add https://public.outreach2day.com/mcp in the assistant and sign in with your Outreach2day account when it asks; curl -fsSL https://outreach2day.com/install | sh does this for every client on your computer at once. Only header-only setups (the xAI API, n8n, CI) use a key, read from $OUTREACH2DAY_API_KEY

3. Give read access first. Workspaces, domains, mailboxes, warmup state and replies; allow writes (warmup operations, replies) only with an approval step

4. Put the sending rules in the assistant's instructions (list below), so its drafts and plans follow them

5. Follow the assistant's guide in the table above, and compare its first answers with the app

The Rules Every Assistant Should Follow

These are the numbers we use with customers; the cold email guide explains them:

• At most 25 cold emails per mailbox per day, and 5 mailboxes per domain (about 125 cold emails per domain per day).

• At least 14 days of warmup before a mailbox sends cold email, with warmup kept on while it sends.

• Follow-ups after 2, 3, 5 and 5 days.

• No links in cold emails, the signature included.

• Heavy spintax on subjects when sending at volume, so the same subject line does not repeat thousands of times.

The same rules are packaged as agent skills in our skills library, for example the follow-up sequence planner. Each assistant's prompts page turns them into copy-paste prompts: Claude, Claude Code, ChatGPT, Grok, Gemini, Cursor and Le Chat.

The Hosted MCP Server

The hosted Outreach2day MCP server is live at https://public.outreach2day.com/mcp. Clients with MCP OAuth add the URL and sign in to Outreach2day on first use, with no API key: Claude Code, Claude Desktop and claude.ai connectors, the ChatGPT app, Codex, Cursor, VS Code, Windsurf, Gemini CLI, grok.com and the Gemini app (Le Chat and Copilot Studio per their docs, not tested by us yet). Clients that only send a fixed header use an API key in the Authorization header, read from $OUTREACH2DAY_API_KEY; the local servers in the other guides are optional. Setup per client is on the MCP page.

https://public.outreach2day.com/mcp

To set up every MCP client on your computer at once:

curl -fsSL https://outreach2day.com/install | sh

Assistants We Left Out

• Perplexity. Its help center documents local MCP servers in the Mac app, with remote servers "coming soon". We could not confirm a launch date or a custom remote connector, so there is no guide yet.

• Zapier. Zapier is retiring Zapier Agents in favour of AI steps inside Zaps. We could not confirm from Zapier's documentation that those steps call a custom API as a tool.

FAQ

Which AI assistant is best for cold email?

For live data today: a coding agent (Claude Code, Cursor, Copilot, Windsurf, Gemini CLI or Grok Build) or Claude, signed in to the hosted MCP server. For scheduled reports: n8n. For a team without developers: Claude or ChatGPT with the server URL added as a connector and an Outreach2day sign-in.

Can an AI assistant run my whole cold email setup?

With the hosted MCP server it checks domains, quotes orders you pay on Stripe, starts warmup, launches campaigns after 14 days of warmup and your confirmation, and reads replies. Sending replies emails real people, so a person should approve those.

Do I need MCP?

No. MCP makes the connection shorter, but every route marked "yes" in the table works over the REST API today.

Is the Outreach2day API included in my plan?

Yes. API access is part of every plan; you pay for mailboxes and domains. See pricing.

Is there an Outreach2day MCP server?

Yes. Add https://public.outreach2day.com/mcp to your assistant and sign in with your Outreach2day account; curl -fsSL https://outreach2day.com/install | sh adds it to every MCP client on your computer at once. You can also build a local one over the public API in about 110 lines of Python.

Related

• Outreach2day MCP: the hosted MCP server and its per-client pages

• Cold email API: endpoints, limits and errors

• Cold email MCP server: the local server the guides use

• Triage cold email replies with AI

• Build an AI SDR with MCP: the workflow, its limits and the cost against AI SDR products

Create an account and add mailboxes, then add the MCP server to your assistant and sign in; for header-only setups, create a key on the API keys page.