LMCP is a cross-platform MCP server (Model Context Protocol) that connects AI assistants — Claude, ChatGPT, Cursor, Windsurf, VS Code, Zed — to your apps: Mail, Microsoft Outlook, Calendar, Microsoft Teams, OneDrive, Slack and Office. On macOS it also reaches native apps. 251 tools. It runs entirely on your machine — no cloud servers, no API tokens, no data leaves your device.

Can LMCP access Microsoft Teams without Graph API?

Yes. LMCP reads Teams messages directly from the local IndexedDB cache on your machine. No Microsoft Graph API, no OAuth tokens, no Azure AD, no API rate limits. Zero network requests to Microsoft.

Is LMCP GDPR compliant?

Yes, by architecture — not by policy. All data is processed on your machine. No personal data is ever transmitted to any server. Your emails, calendar, contacts, Teams messages and files never leave your device. Inherently compliant with GDPR, CCPA and similar regulations.

How does LMCP differ from other MCP servers?

LMCP is the only MCP server that: (1) runs 100% locally with zero cloud dependencies, (2) reads Microsoft Teams without Graph API tokens, (3) accesses native apps directly instead of cloud APIs, (4) requires no OAuth setup or API keys, (5) works offline once installed.

Yes. LMCP is free to install and use. No credit card, no API keys, no subscription. It works with Claude, ChatGPT, Cursor, VS Code and any MCP-compatible client.

Read Slack Messages with AI (Claude, Cursor, VS Code)

Why Other Solutions Require a Slack App and Token

Connecting an AI assistant to Slack the official way means going through Slack's Web API, which requires:

A Slack app — you have to create and configure an app in the Slack developer console
OAuth scopes — pick the right read scopes (channels:history, groups:history, search:read…), which is fiddly and easy to get wrong
Workspace-admin approval — many workspaces require an admin to install or approve the app, and most won't for a personal tool
Token management — bot/user tokens to store securely and rotate
Rate limits — Slack throttles the API, and search in particular is limited

For an individual who just wants their AI to catch them up on Slack, that's a lot of overhead — and often a hard blocker if your workspace admin won't approve apps.

How LMCP Reads Slack Differently

LMCP skips the Slack API entirely. Instead of creating an app and managing tokens, it reads Slack data from the local cache the Slack desktop app keeps on your Mac.

The Slack desktop app is an Electron app that stores your workspaces, channels, and recent messages in an IndexedDB database (backed by LevelDB) on disk — part of how it works offline and loads instantly. If you're signed into Slack on your Mac, that data is already on your machine.

LMCP reads that database directly with a specialized parser. No Slack app, no OAuth scopes, no admin approval, no tokens. Read-only by design — it never sends or changes anything.

What You Can Access

Through LMCP, your AI assistant can:

List your workspaces — every Slack workspace you're signed into
List channels — browse channels and DMs in a workspace
Read channel messages — pull recent message history from a channel
Search messages — find messages across your channels by topic or keyword

This is read-only access — LMCP reads what's cached on your machine and cannot post, edit, or delete anything in Slack.

How to Install

Download LMCP and install it:

Open the downloaded .dmg file from your Downloads folder
Drag Local MCP to your Applications folder
Open Local MCP from your Applications folder — it appears in your menu bar

Takes about 30 seconds. Your AI clients are configured automatically.

After installation, restart your AI client so it picks up the new MCP tools:

Claude Desktop — quit completely (Cmd+Q) and reopen
Cursor — restart the editor
VS Code — reload the window (Cmd+Shift+P → “Reload Window”)
ChatGPT / Windsurf — restart the application

Make sure the Slack desktop app is installed and you're signed in. LMCP detects your Slack data automatically — no API keys, no app to create.

Example Prompts

Once connected, try these with your AI assistant:

“Catch me up on my Slack channels from today” — summarizes recent activity across your channels
“What did the team say in #engineering this morning?” — reads and summarizes a specific channel
“Search my Slack for messages about the launch” — finds relevant discussion across channels
“Did anyone @ me with something I need to act on?” — scans recent messages for action items
“Summarize the #incidents channel this week” — aggregates a busy channel into the key points

Slack is where catching up is most painful — dozens of channels, hundreds of messages. Letting your AI read and summarize them turns an hour of scrolling into one prompt.

Limitations

Because LMCP reads from the local cache rather than a live API, keep these in mind:

Only cached messages are available — Slack caches recent conversations; channels you haven't opened in a long time may not be fully on disk
Read-only — you can read but not send, edit, or delete messages
Requires the Slack desktop app — the browser version doesn't create a local cache LMCP can read
Cache freshness — the cache reflects the last time Slack synced; keep Slack running for up-to-date data
Multiple workspaces — if you're signed into several, LMCP can read all of them

Technical Deep-Dive: How LevelDB Parsing Works

For the technically curious, here's how LMCP extracts Slack data from the local cache.

The Slack desktop app stores its IndexedDB data on macOS at paths such as:

~/Library/Application Support/Slack/IndexedDB/*.leveldb ~/Library/Containers/com.tinyspeck.slackmacgap/Data/Library/Application Support/Slack/IndexedDB/*.leveldb

This is a Chromium-style LevelDB database — the same format Chrome and other Electron apps use. LMCP parses it with the open-source ccl_chromium_reader library (originally built for digital forensics), which handles Chromium's V8 serialization, LevelDB's append-only log and compaction, and IndexedDB's object stores. The parsed records are filtered into clean JSON — channels, messages, senders, timestamps — that your AI assistant can work with.

The database is opened read-only by design. LMCP cannot corrupt or modify your Slack cache.

Compared to Other Approaches

Slack Web API + custom app — full read/write but needs an app, OAuth scopes, and (often) admin approval. Best for teams building a real Slack integration.
Zapier / automation tools — connect Slack to other apps but still rely on a Slack app/token and route data through a third party.
LMCP (local cache) — read-only, zero configuration, runs entirely on your Mac. Best for individuals who just want their AI to read and summarize Slack.

Real-World Workflows

The value isn't reading one message — it's having your AI synthesize across channels and connect Slack to your other tools.

Morning catch-up

Summarize everything I missed in Slack overnight across my channels, grouped by channel, and flag anything that needs a reply from me.

Instead of opening 20 channels, your AI reads them all and hands you one prioritized digest.

Turn Slack threads into tasks

Go through my Slack from today, find anything that looks like a commitment I made, and create reminders for each with who asked and when.

Commitments hide in chat — “I'll send that over”, “let me check”. Your AI surfaces them and (with LMCP's Reminders/OmniFocus tools) turns them into tasks.

Cross-app meeting prep

Check what was discussed about Project X in Slack this week, pull any related emails, and prep a briefing with open questions for tomorrow's meeting.

Because LMCP also reads your email, calendar, and files, your AI can pull a complete picture across tools — not just Slack.

LMCP also connects your AI assistant to email, Microsoft Teams, Calendar, Contacts, OneDrive, and local files. See the full list of guides or learn more at local-mcp.com.

Read Slack Messages with AI (Claude, Cursor, VS Code) — No Tokens, No Slack App