Skip to content
MCP server

MsgLens

Read Outlook .msg, .eml and winmail.dat files locally: headers, body and attachments

Runs locallyStatus and history
Install
Pricing
Free
Platforms
CLI, Web
Runs
Locally
Version
0.2.1
Listing updated
1 day ago

About MsgLens

MsgLens is a free MCP server for files and documents. It runs locally on your machine and is started by your AI client.

Most Outlook messages keep their body only as compressed RTF with HTML wrapped inside, so parsers that read only the HTML or text fields return empty bodies. This one decompresses the RTF and falls back through the available body fields, detects the format from the bytes so renamed files still open, unpacks winmail.dat, and decodes non-Latin text using the declared code page. It also reads saved appointments and contacts.

The MCP server runs over stdio with three tools to read an email, save its attachments and convert to .eml or .txt, and it makes no network requests. Message text is written by whoever sent it, so the tools instruct the assistant to treat it as data. The same parsers power a browser viewer at msglens.app that processes files locally with a 100 MB limit.

The CLI also converts folders of .msg files and never overwrites existing files.

Install

Run in a terminal

claude mcp add msglens -- npx -y msglens-cli

Add to claude_desktop_config.json

{
  "mcpServers": {
    "msglens": {
      "command": "npx",
      "args": [
        "-y",
        "msglens-cli"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "msglens": {
      "command": "npx",
      "args": [
        "-y",
        "msglens-cli"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "msglens": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "msglens-cli"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "msglens": {
      "command": "npx",
      "args": [
        "-y",
        "msglens-cli"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "msglens": {
      "command": "npx",
      "args": [
        "-y",
        "msglens-cli"
      ]
    }
  }
}

Tools this server provides (3)

Taken from the project documentation; the running server may differ.

read_email
Subject, sender, recipients, date, body and attachment list
save_attachments
Write every attachment into a folder
convert_email
Convert .msg or winmail.dat to .eml or .txt

What it does

Reliable body extraction
Handles RTF-wrapped HTML bodies that other parsers miss.
winmail.dat support
Unpacks attachments trapped in TNEF files.
Attachment saving
Writes attachments to a folder without overwriting.
Format conversion
Converts .msg or winmail.dat to .eml or .txt.
No network calls
Files stay on your machine.
Library and CLI
Usable from Node or the command line.

Good for

  • Summarise an .msg file someone sent you
  • Extract attachments from a winmail.dat
  • Convert a folder of .msg files to .eml
  • Read Outlook items without Outlook

Pricing

Free

Free; installs from npm

Prices change. Check msglens.app before you buy.

MsgLens FAQ

Does it upload my emails?

No. The README says the server makes no network requests.

How do I add it to Claude Code?

Run claude mcp add msglens -- npx -y msglens-cli mcp.

What formats does it open?

Outlook .msg, .eml and winmail.dat.

Is there a web viewer?

Yes, msglens.app parses files in the browser.

Is MsgLens free?

Yes. MsgLens is free to use.

How do I add MsgLens to Claude Code?

Run this command in your terminal: claude mcp add msglens -- npx -y msglens-cli

What are the best alternatives to MsgLens?

The closest alternatives to MsgLens are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to MsgLens

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools