Hosted MCP server

Give your AI assistant full OutreachFox superpowers

The OutreachFox MCP server connects Claude, Cursor, Windsurf, and any MCP-compatible AI directly to your outreach workflows — 158 tools covering sequences, contacts, mailboxes, unified inbox, warmup, LinkedIn automation, webhooks, and analytics.

Get your API key View API docs

AI chat · via MCP

You: "List my active sequences and their reply rates"

AI:

You have 3 active sequences:

"Q3 Outbound" — 1,240 sent, 8.2% reply rate
"Inbound Follow-up" — 856 sent, 12.1% reply rate
"Re-engagement" — 412 sent, 4.9% reply rate

What is MCP?

One open standard, every AI client

Model Context Protocol is an open standard that lets AI assistants call external tools securely.

Our hosted server at https://mcp.outreachfox.ai translates MCP calls into OutreachFox API requests — no self-hosting, no setup beyond adding a URL and your API key.

158tools available

1URL to connect

60 req/minrate limit (10/min for inbox & LinkedIn)

0infrastructure to host

Installation

Connect in under 2 minutes

Server URL: https://mcp.outreachfox.ai — authenticate with your OutreachFox API key (Dashboard → Settings → API Keys).

https://mcp.outreachfox.ai

Add to claude_desktop_config.json — macOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%\Claude\claude_desktop_config.json. Then restart Claude Desktop.

{
  "mcpServers": {
    "outreachfox": {
      "type": "http",
      "url": "https://mcp.outreachfox.ai",
      "headers": {
        "apikey": "YOUR_OUTREACHFOX_API_KEY"
      }
    }
  }
}

What can you do?

Run outreach from a chat window

Campaign management

"Pause my re-engagement sequence and clone Q3 Outbound"

Lead import

"Create a list called SaaS Founders and import these 50 contacts"

Deliverability monitoring

"Check DNS and warmup health across all my domains and mailboxes"

Unified inbox triage

"Show me unread positive replies from this week and draft responses"

Analytics

"Compare step-level open and reply rates for my top 3 sequences"

LinkedIn outreach

"List my connected LinkedIn accounts and their daily limit usage"

Notes & limits

Most tools require a workspace_id — just ask the assistant to "list my workspaces" first and it will use the right ID for the rest of the session.
Rate limits follow the public API: 60 requests/minute for most endpoints, 10 requests/minute for inbox, LinkedIn, and warmup endpoints.
Your API key is sent only from your AI client directly to our server over HTTPS — it is never logged or stored by the MCP server.

Ready to automate outreach with AI?

Get your API key Read the full API documentation →