Cold Email & Outreach MCP Server
Enables AI agents to draft evidence-grounded cold-email openers, A/B variants, personalized LinkedIn DMs, and SEO content-gap plans for sales and marketing outreach.
README
Cold Email & Outreach MCP Server - Personalize Email & LinkedIn

Give your AI agent 4 generation tools: draft evidence-grounded cold-email openers, A/B variants, personalized LinkedIn DMs, and SEO content-gap plans. For sales and marketing agents that need to write, not just retrieve. Runs in Apify Standby mode (warm, responds in seconds). Free to try right now (in the 14-day price-notice window), then $0.10 per tool call.
Who uses this
- SDRs & AEs drafting evidence-grounded cold-email openers that reference real prospect detail.
- Agencies running personalized outreach across many accounts without a copywriter per campaign.
- Founders doing their own sales who need A/B variants and LinkedIn DMs fast.
- AI agents that write outreach, not just retrieve data.
Connect in 30 seconds
The server speaks Streamable HTTP at /mcp. Add this to your MCP client config:
{
"mcpServers": {
"ai-outreach": {
"url": "https://fetchcraft--ai-outreach-mcp.apify.actor/mcp?token=YOUR_APIFY_TOKEN"
}
}
}
Works in Claude Desktop, Cursor, Cline, Windsurf, VS Code, and any Streamable-HTTP MCP client.
Get your token: sign in at apify.com, then Settings, then Integrations, then copy your Personal API token. Paste it in place of YOUR_APIFY_TOKEN. The first call wakes the standby server (about 5 seconds); after that, calls are instant.
Test it works (replace the token):
curl -s -X POST "https://fetchcraft--ai-outreach-mcp.apify.actor/mcp?token=YOUR_APIFY_TOKEN" \
-H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
What you get
A representative result (clean structured JSON):
{
"company_name": "Airtable",
"opener": "I saw Airtable now embeds AI agents into workflows...",
"fit_score": 85,
"channel": "email"
}
Tools
| Tool | What it does |
|---|---|
personalize_cold_email |
Opener grounded in evidence quotes from a company site |
rewrite_cold_email |
Turn a draft into multiple AI variants for A/B testing |
personalize_linkedin |
A LinkedIn comment/DM that references the prospect post |
seo_content_gap |
SEO content gaps vs a competitor with target keywords |
Each tool runs a maintained fetchcraft Apify Actor under the hood and returns clean structured JSON. No LLM key, no scraping infrastructure to manage.
Example agent prompts
- "Write a cold-email opener for airtable.com selling RevOps automation." ->
personalize_cold_email - "Give me 3 variants of this cold email." ->
rewrite_cold_email - "Draft a LinkedIn reply to this VC post." ->
personalize_linkedin
Why pay-per-call beats a subscription
- No subscription, no seats, no minimums. You pay $0.10 per call, only for what you actually use. Comparable tools in this space usually lock you into a monthly plan whether you run it or not.
- No LLM key and no scraping infrastructure to manage. Connect your Apify token and the maintained Actors do the work, returning clean structured JSON.
- Built for AI agents. Drop-in MCP server over Streamable HTTP for Claude Desktop, Cursor, Cline, Windsurf, and VS Code.
- $5/month in free Apify platform credits on every account, that is 50 free calls every month, indefinitely.
Pricing
- Free right now. Every tool call is free during the 14-day price-notice window.
- After that: $0.10 per tool call, flat. No subscription, no seat licenses, no minimum.
- Every Apify account includes $5/month in free platform credits (= 50 free tool calls every month).
FAQ
Which MCP clients work? Any client supporting Streamable HTTP: Claude Desktop, Cursor, Cline, Windsurf, VS Code, and others.
Do I need an LLM key? No. Connect your Apify token and go.
Is the first call slow? Only the very first one, while the standby server wakes (about 5 seconds). Subsequent calls are instant.
Can I get the full fetchcraft suite? Yes, 28 scrapers plus 6 MCP servers under the fetchcraft publisher. Storefront: https://ai-sales-personalizer.vercel.app/scrapers
Support
Found a bug or want a new tool? Open an issue on the Actor's Issues tab.
Last Updated
2026-06-18
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.