Email Outreach by OpenHelm

Run personalised outreach campaigns and manage conversations using a virtual computer equipped with email capabilities, research tools, and workflow automation.

CommunityOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • Research Recipient: Research a person or business from public sources before emailing them: who they are, what the organisation does, specific current hooks worth referencing, the best contact email i
  • Draft Outreach Email: Draft (without sending) one personalised outreach email to accomplish a stated objective — a one-line reason, a single clear ask, and an easy way to respond, under 120 words, gro
  • Send Outreach Email: Compose and SEND one personalised outreach email via your connected email account to accomplish a stated objective. Requires an email connection; if none is set up the run stops a

What data it sees

Do you need an account

No: the server works without sign-in

Run personalised outreach campaigns and manage conversations using a virtual computer equipped with email capabilities, research tools, and workflow automation.

Email Outreach by OpenHelm enables your agent to carry out work such as:

• Prospect research • Personalised outbound email campaigns • Lead qualification • Follow-up sequences • Inbox monitoring and response handling

What makes OpenHelm the best solution for this:

• AI continuously monitors conversations and adjusts actions to maximise outcomes • Deep research capabilities enable highly personalised outreach at scale • Multi-step workflows coordinate research, sending, follow-ups, and response management • Operates within a secure remote environment isolated from your local machine

For organisations looking to generate opportunities through outbound communication, OpenHelm provides the infrastructure needed to run sophisticated outreach workflows autonomously.

How to connect

How to connect Email Outreach by OpenHelm to Claude

The server address to paste into Claude settings:

https://email-outreach-by-openhelm.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Email Outreach by OpenHelm to ChatGPT

The server address to paste into ChatGPT settings:

https://email-outreach-by-openhelm.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Email Outreach by OpenHelm to Cursor

The server address to paste into Cursor settings:

https://email-outreach-by-openhelm.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (6)

Raw names from tools/list. Only developers need these.

research_recipientResearch a person or business from public sources before emailing them: who they are, what the organisation does, specific current hooks worth referencing, the best contact email if discoverable, and the angle most likely to earn a reply — each claim source-cited. Use to personalise outreach. Returns a structured dossier.
draft_outreach_emailDraft (without sending) one personalised outreach email to accomplish a stated objective — a one-line reason, a single clear ask, and an easy way to respond, under 120 words, grounded in real research. Use when you want to review before sending. Returns the subject and body.
send_outreach_emailCompose and SEND one personalised outreach email via your connected email account to accomplish a stated objective. Requires an email connection; if none is set up the run stops and says so rather than pretending to send. Use to actually reach out. Returns the subject, body sent, recipient and provider message id.
triage_inboxRead your connected inbox and triage recent replies: per thread, who replied, a one-line summary, sentiment, whether it needs a human, and the recommended next action. Use to stay on top of an outreach campaign's responses. Returns the triaged threads.
draft_replyDraft (without sending) a reply to an inbound message that advances a stated objective — answering only what can be supported truthfully and flagging anything that needs a human. Use to respond to a reply safely. Returns the reply body and a needs_human flag.
check_resultRetrieve the result of a previously started OpenHelm task. Use this when an earlier tool returned status "running" together with a task_id — call check_result with that task_id to get the finished result (or the current status if it's still running). Returns the structured result, confidence, evidence (screenshot URL + matched text), and usage when the task has succeeded.