Inbox MCP
Transform your inbox into an intelligent, LLM-powered assistant that manages, organizes, and streamlines email using conversational language. Compatible with Gmail, Outlook, iCloud, Yahoo, and IMAP services through Nylas v3 API.
README
Inbox MCP
Transform your inbox into an intelligent, LLM-powered assistant—instantly.
Easily manage, organize, and streamline your email using conversational language, powered by robust, batch-friendly tools built on Nylas v3. Compatible out-of-the-box with Gmail, Outlook, iCloud, Yahoo, and virtually any IMAP service (even your work email!).
Tools are carefully crafted with clear descriptions and consistent parameters optimized for seamless integration with various LLMs. Responses are provided as easily parsable XML blocks, allowing the LLM to effortlessly handle your requests.
Tested extensively in real-life workflows, Inbox MCP significantly reduces cognitive load, efficiently handling tasks you’d rather automate.
Nylas includes 5 free connected accounts, so you can get started immediately—without spending a dime.
✨ Real-life examples (things you'll actually say)
| You casually say… | Inbox MCP effortlessly handles it by… |
|---|---|
| “take a look at my inbox and LMK what's important and what i have to act on” | Reviewing your messages, quickly identifying actionable emails, and summarizing what needs attention. |
| “Find the unimportant emails from my last 100 and move them to the Unimportant folder.” | Intelligently filtering out low-priority emails and neatly organizing them out of sight. |
| “Archive everything older than two weeks, except starred emails.” | Batch-archiving older emails while safely preserving your starred messages. |
| “Summarize and forward the latest AWS alerts to my team.” | Compiling recent AWS alerts into a concise summary and sending it off immediately. |
🎯 Why use Inbox MCP?
- Inbox Zero, Simplified: Quickly automate email management using natural language instructions.
- Efficient Triage: Instantly categorize, prioritize, and batch-process emails effortlessly.
- Easy Setup: Hassle-free onboarding with direct account connections. No OAuth tokens, proxies, or complex setups.
📌 Quick Setup: Creating a Nylas Account
- Sign up at: Nylas Dashboard.
- Grab your API key from the sidebar (
API KEY).

- Navigate to
Grants, clickAdd Test Grant(top-right), and connect your email account.

- Note your API key and Grant ID (shown in the grants table).
🚀 Get started (in under a minute)
Easy Smithery Installation (Interactive)
Inbox MCP integrates seamlessly with MCP clients like Claude Desktop, Cursor, Windsurf, and more.
Interactive one-liner installation (recommended):
npx -y @smithery/cli@latest install "@darinkishore/inbox-mcp" --client claude
This will prompt you for your Nylas credentials (nylasAccessToken and nylasGrantId). For other supported MCP clients, replace claude with your preferred client:
npx -y @smithery/cli@latest install "@darinkishore/inbox-mcp" --client cursor # or windsurf, vscode, etc.
🛠️ Manual local setup (optional)
If you prefer manual control for local development:
git clone https://github.com/darinkishore/Inbox-MCP.git
cd Inbox-MCP
npm install && npm run build
Then in your MCP client's mcp-config.json:
{
"mcpServers": {
"nylas-email": {
"command": "node dist/index.js",
"workingDirectory": "/absolute/path/to/Inbox-MCP",
"env": {
"NYLAS_ACCESS_TOKEN": "...",
"NYLAS_GRANT_ID": "..."
}
}
}
}
🔧 Daily workflow tools (optimized)
| Tool | What it does (in plain English) |
|---|---|
filter_emails |
Find emails quickly by folder, unread status, dates, or flags. |
triage_update_emails |
Batch-update emails as read/unread, starred/unstarred, or move folders. |
batch_archive_emails |
Archive groups of emails safely and quickly. |
search_emails |
Search emails rapidly with simple keyword queries. |
read_emails |
Fetch complete emails formatted neatly in Markdown, ideal for summaries. |
send_email / draft_email |
Easily compose and send (or draft) new emails. |
| Folder management tools | (list_, create_, update_, delete_, get_or_create_) |
🗺️ Roadmap
- Enhanced provider-native search (advanced queries, multi-term searches)
- Calendar and contacts integration
- Expanded toolset and automation capabilities
👩💻 Developer-friendly
- Clean TypeScript (v5.2), minimal dependencies
- Robust built-in retries (exponential back-off + jitter)
- Contributions warmly welcomed—let's make email management better together!
📄 License & Support
Licensed under MIT.
If Inbox MCP makes your day easier, please ⭐️—your star helps others discover it too!
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.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.