Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@openoutbound What needs my attention? Then draft 5 sample emails for review."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An engine, not a prompt. Sending limits, approvals, suppression lists, compliance rules and budgets are enforced by code. An agent cannot blast 300 LinkedIn invites or email someone who unsubscribed, even if it tries.
Any agent, any brain. One registry powers an MCP server, an Agent Skill, a CLI and a REST API. Drive it from Claude, Codex, Cursor or a cron job. Think with Anthropic, OpenAI, OpenRouter, a local model, or your own Claude or ChatGPT subscription.
Every part is a plug-in. Your mailboxes, your data providers, your LinkedIn provider, your CRM. Skip what you do not need; it still works with nothing but a CSV and one mailbox.
Related MCP server: sales-intelligence
Try it in the sandbox: two demo client workspaces with fake mailboxes, fake prospects and simulated replies. Nothing leaves your machine and no API keys are needed. You need Node 22+ and pnpm (corepack enable).
git clone https://github.com/xyluxx/openoutbound && cd openoutbound
pnpm install && pnpm build
node dist/cli/main.js init # .env with a fresh secret key, local database
node dist/cli/main.js sandbox # seeds the demo workspacesConnect your agent from the same folder (Claude Code shown; Codex, Cursor, VS Code and others). init prints this command with your paths filled in.
claude mcp add openoutbound -- node "$PWD/dist/cli/main.js" --home "$PWD" mcp --workspace northwindThen ask it:
What needs my attention in OpenOutbound? Then draft a campaign for our best offer and show me five sample emails before anything is sent.
Going live: install with Docker, connect mailboxes, pick an AI brain.
The engine does the repetitive work on a schedule: sequencing, sending, reply sync, signal monitors, reports. Agents and people steer it through four doors. Every call passes the same safety gate: scopes, limits, approvals, budgets and an audit log with the reason for each action.
Leads | Import CSV, Excel or JSON, search Apollo or Google Maps, or hand over a list. Dedupe, ICP fit scoring with reasons, email finding and verification. |
Research and signals | Sourced research briefs. 15 built-in buying signals plus your own, written in plain English. Free collectors for website changes, job boards, news and tech stack. |
Campaigns | As many as you want, each with its own offer, senders, schedule, review level, writing rules and priority. Email and LinkedIn steps, waits, branches, A/B variants, templates. |
AI writing you can check | Every fact about a prospect has a source. A checker reviews every message. Review every message, only first messages, or only when the checker is unsure. Preview on real leads and teach it with corrections. |
Sending | Your own mailboxes over SMTP/IMAP or OAuth. Daily caps, ramp-up, recipient-timezone windows, one-click unsubscribe, bounce auto-pause. |
Profile visits, likes, comments, invites and messages inside conservative limits. Posting through LinkedIn's official API. | |
Inbox | Replies from every channel in one place, classified, with the right next step and drafted answers. Unsubscribes, angry replies and prompt-injection attempts are handled by locked rules. |
Reports | Funnels by step and variant, sender health, which signals lead to meetings, pipeline, AI and data costs, scheduled summaries to Slack or email. |
Compliance built in | Consent-required countries, unsubscribe and postal address in every email, suppression everywhere, ad and AI disclosure lines, data retention. |
Agency ready | Many client workspaces, scoped API keys, budgets per workspace, a kill switch, an audit log, a cross-client report. |
Slot | Built in |
AI brain | Anthropic, OpenAI, OpenRouter, Gemini, Ollama, LM Studio, any OpenAI-compatible API, Claude Code CLI, Codex CLI, or your connected agent |
Lead data | CSV, Excel, JSON, Apollo, Google Maps |
Email finder and checker | Icypeas, Findymail, Hunter, Prospeo, MillionVerifier, Reoon, built-in website crawler |
Research | Parallel, Exa, Tavily, Firecrawl, built-in fetcher |
Signals | Built-in collectors, PredictLeads, Crustdata, any tool via webhook |
Unipile for outreach, LinkedIn official API for posting | |
CRM and alerts | HubSpot, Pipedrive, webhooks, Slack, email |
Need something else? Write a provider in one file.
Start: Quickstart · Install · Connect your agent · Sandbox
Understand: How it works · Safety and approvals · Campaigns · Signals · Reports
Set up: AI brain · Mailboxes · LinkedIn · Lead sources · Deploy
Reference: MCP tools · CLI · REST API · Configuration
Playbooks: ICP · Signals · Copywriting · Sequences · Deliverability · LinkedIn · Replies · Compliance
v0.1 is an early release. The engine, doors and providers are covered by tests against recorded fixtures; real-world provider behavior can differ, so start in the sandbox, then with low volume. See the roadmap.
Issues and pull requests are welcome. Read CONTRIBUTING.md and AGENTS.md. Security issues: SECURITY.md.
This server cannot be deployed
Human-in-the-loop LinkedIn outreach and a built-in sales CRM for AI agents. Safety-gated, anti-spam.
Find LinkedIn prospects, draft outreach, and run human-paced campaigns from your AI agent.
Find and enrich leads, run multi-channel outreach, and manage the sales pipeline.
Run B2B outreach from your AI agent: 250+ tools for campaigns, leads, LinkedIn and email workflows.
