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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。