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>
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.