mcpField
I
Inbox MCP

Inbox MCP

Local
github.com/darinkishoreCommunication21Updated 79w ago

About Inbox MCP

Inbox MCP is an MCP server that connects to email accounts through Nylas, letting AI assistants batch-triage, organize and automate mail using natural language. It supports Gmail, Outlook, iCloud, Yahoo and IMAP services, aimed at users who want less manual inbox work.

Key features

  1. 01Batch filtering of emails by folder or status
  2. 02Batch updates for read, star and folder
  3. 03Batch archiving of emails
  4. 04Keyword search and Markdown email reading
  5. 05Sending and drafting emails
  6. 06Folder create, update and delete tools

Use cases

  1. 01Identifying emails that need action
  2. 02Moving low-priority mail to a separate folder
  3. 03Archiving older mail while keeping starred messages
  4. 04Summarizing alert emails and forwarding them to a team

MCP support

The project runs as an MCP server that exposes filtering, search, update, archive and send tools to MCP clients. Responses are returned as XML blocks that LLMs can parse.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"Inbox-MCP": {
"command": "npx",
"args": [
"-y",
"@smithery/cli"
]
}
}
}
Run commandnpx -y @smithery/cli

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@smithery/cli

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project 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

  1. Sign up at: Nylas Dashboard.
  2. Grab your API key from the sidebar (API KEY).
    API Key location
  3. Navigate to Grants, click Add Test Grant (top-right), and connect your email account.
    Grant ID location
  4. 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)

ToolWhat it does (in plain English)
filter_emailsFind emails quickly by folder, unread status, dates, or flags.
triage_update_emailsBatch-update emails as read/unread, starred/unstarred, or move folders.
batch_archive_emailsArchive groups of emails safely and quickly.
search_emailsSearch emails rapidly with simple keyword queries.
read_emailsFetch complete emails formatted neatly in Markdown, ideal for summaries.
send_email / draft_emailEasily 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!

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.