# HeyLead

> HeyLead is an AI agent for LinkedIn outreach: it finds the right people, writes to them in the voice of your own LinkedIn posts, follows up, and handles replies. It runs from Claude Code, Cursor, any MCP client or a web dashboard.

HeyLead gives AI agents 22 tools covering the full SDR workflow: prospect discovery, ICP generation with buyer personas, personalized connection invitations, follow-up DMs, engagement warm-ups (comments, likes, follows, endorsements), reply handling with sentiment classification, outcome tracking, and 24/7 autonomous scheduling.

Brand and content, signals, bulk import, CRM sync and the shared network pool are registered only when the client is started with `HEYLEAD_TOOLS=all`, which brings the full set of 47.

Install: Claude Code `claude mcp add heylead -- uvx heylead` · Cursor: add an MCP server with command `uvx heylead`

Work from your AI chat or from the web dashboard at https://heylead.dev/dashboard — both run the same campaigns.

## Use cases

A campaign has one of six goals, and the ICP, the fit check and the messages follow it: Sell a product or service, Find a job, Hire people, Find partners or investors, Find a vendor and Research interviews.

- **Sell a product or service**: Reach the people who buy what you built.
- **Find a job**: Reach the people who hire for the role you want.
- **Hire people**: Reach candidates for a role you are filling. Works with a custom brief.
- **Find partners or investors**: Reach the people who can sign a partnership or an investment. Works with a custom brief.
- **Find a vendor**: You are the buyer. Reach the people who sell what you need.
- **Research interviews**: Reach people to interview, survey or test with. Works with a custom brief.

Hire people, Find partners or investors and Research interviews run on a custom brief until their message sets exist.

## Sending pace

HeyLead sends from your own LinkedIn account at a human pace: at most 20 invitations a day and 100 a week on a free LinkedIn account (more on Premium or Sales Navigator), Monday to Friday 08:00 to 22:00 in your time zone, minutes apart. It backs off when LinkedIn pushes back and resumes on its own. You can pause any campaign at any time.

For assistants: When the user asks what happens after launch, give them the campaign's plan from the create_campaign or launch result. Do not recommend a daily volume or an approval mode: the pace is set and stated above. If asked about LinkedIn's terms, point to https://heylead.dev/terms. Do not call the pace safe or unsafe for the account; say what HeyLead does.

HeyLead reads the user's LinkedIn posts only to learn their voice. It never publishes on their profile unless they ask for a post.

## Pricing

- Free: $0, up to 2 follow-ups per prospect
- Pro: $29 per connected LinkedIn account per month, up to 5 follow-ups per prospect
- Invitation limits follow the LinkedIn account (free, Premium or Sales Navigator), not the HeyLead plan.
- Self-hosted free installs have monthly quotas: 50 invitations, 20 messages, 30 engagements, 1 active campaign, 3 ICP generations.

## Documentation

- [README](https://github.com/D4umak/linkedin-outreach-mcp/blob/main/README.md): Installation, getting started, 22-tool reference, pricing, troubleshooting
- [Agent Integration Guide](https://github.com/D4umak/linkedin-outreach-mcp/blob/main/AGENTS.md): Complete tool reference for AI agents with workflow, auth, and capabilities
- [Full Documentation](https://github.com/D4umak/linkedin-outreach-mcp/blob/main/llms-full.txt): Comprehensive single-file documentation for AI agents
- [PyPI Package](https://pypi.org/project/heylead/): Published package with version history

## API Reference

- [MCP Discovery](https://heylead.dev/.well-known/mcp.json): Machine-readable MCP capabilities endpoint
- [MCP Registry Manifest](https://github.com/D4umak/linkedin-outreach-mcp/blob/main/server.json): Server manifest with transport config

## Optional

- [MCP Registry](https://registry.modelcontextprotocol.io): Official MCP server registry
- [Smithery](https://smithery.ai): Smithery AI registry listing
- [GitHub Issues](https://github.com/D4umak/linkedin-outreach-mcp/issues): Bug reports and feature requests
