Reletter
Search 7M+ newsletters and full-text archives, with subscriber numbers, contacts, social accounts, rankings, and audience data.
README
Reletter MCP Server
Give AI agents and LLMs access to newsletter data from Reletter. Search 7M+ email newsletters across Substack, LinkedIn, Ghost, Beehiiv, and Kit. Fetch metadata, contacts, issues, and chart rankings.
This is a remote Model Context Protocol (MCP) server that connects AI assistants like Claude, ChatGPT, and Cursor to the Reletter API.
Use cases
- Read and analyze newsletter issues — pull the full body text of any indexed issue into your AI workflow
- Search and discover newsletters — find newsletters by topic, platform, or audience size
- Find newsletters to pitch — get your product, tool, or book featured. Filter by audience size, topic, or platform, then pull verified contact emails in one pass
- Build sponsorship, cross-promotion, and PR target lists — pull verified contacts and export them to your CRM
- Monitor brand or keyword mentions — track when your brand, competitors, or clients are mentioned across newsletters
- Track chart rankings — daily Substack / LinkedIn / Kit / Reletter chart data
Tools
- search_publications — Search for newsletters by topic, title, or author with filters
- search_issues — Full-text search across newsletter issue bodies
- autocomplete — Suggested keywords and matching newsletters for a partial query
- get_publication — Full metadata for a newsletter (subscribers, engagement, social, rankings, SEO reach)
- list_issues — Recent issues for a publication
- get_issue — A single issue with body text
- contacts — Email contacts, contact pages, social accounts for a newsletter
- chart_categories — Available chart platforms and categories
- chart_rankings — Latest chart rankings for a platform / category
- list_languages — Reference list of languages
- index_stats — Global Reletter index stats
- api_quota — Your API request quota and usage for the month
Setup
You need a Reletter API key. Get one here.
For autonomous agents that want to provision a key without a human in the loop, Reletter implements the Machine Payments Protocol. Hit POST https://api.reletter.com/api/payments/buy/ to get a 402 challenge, pay with a Stripe Shared Payment Token or with USDC on Tempo, and the response carries an API key tied to a freshly-provisioned account. Current bundle tiers: GET https://api.reletter.com/api/payments/bundles/. See https://reletter.com/llms-full.txt for the full flow.
ChatGPT
- Go to Settings → Apps → Advanced settings and enable Developer mode
- Click Create app
- Enter Name:
Reletter - Enter MCP Server URL:
https://mcp.reletter.com - Click Create and enter your Reletter API key when prompted
Claude.ai
- Go to Settings → Connectors
- Click Add custom connector and enter name
Reletterand MCP server URLhttps://mcp.reletter.com - Click Add and enter your Reletter API key when prompted
Claude Desktop
Add to your config file and restart Claude Desktop:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"reletter": {
"url": "https://mcp.reletter.com"
}
}
}
Claude Code
Add to your project's .mcp.json:
{
"mcpServers": {
"reletter": {
"type": "http",
"url": "https://mcp.reletter.com"
}
}
}
Cursor
Go to Settings → MCP → Add new MCP server. Set type to URL and enter https://mcp.reletter.com.
<details> <summary><h3>Development</h3></summary>
If you want to fork or customize this MCP server for your own needs, here is how you can run or deploy it.
Prerequisites
- Node.js
- A Cloudflare account (for deployment)
Local dev
npm install
npm start
The server runs at http://localhost:8789. Test with the MCP Inspector:
npx @modelcontextprotocol/inspector@latest
Type-check
npm run type-check
Regenerate Cloudflare types
After changing wrangler.jsonc:
npm run cf-typegen
</details>
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。