Slunk

Provides real-time Slack search and analytics via an MCP server that integrates with Claude Desktop on macOS.

other

9

GitHub Stars

other

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "kimjune01-slunk-mcp": {
      "command": "/path/to/slunk-swift.app/Contents/MacOS/slunk-swift",
      "args": [
        "--mcp"
      ]
    }
  }
}

Slunk MCP Server enables Claude Desktop to query Slack messages in real time with semantic search, storing results locally on your machine and exposing powerful search tools through a simple MCP interface.

How to use

You connect an MCP client like Claude Desktop to Slunk MCP Server to perform natural language and structured searches over your Slack messages. Use the available tools to search conversations, filter by channel or user, retrieve complete thread contexts, and discover patterns or related conversations. The server runs locally and stores data on your machine for privacy and fast access.

How to install

Prerequisites: macOS 13.0+ and Xcode 15.0+ installed on your Mac. Ensure the Slack desktop app is installed and running.

Build Slunk and run the GUI.

Build and run the Slunk MCP server

# Build
cd slunk-swift
xcodebuild -project slunk-swift.xcodeproj -scheme slunk-swift -configuration Release build

Launch the GUI (menu bar app) after the build completes.

Configure Claude Desktop to use the MCP server by adding the following JSON configuration in the Claude Desktop settings.

{
  "mcpServers": {
    "slunk-swift": {
      "command": "/path/to/slunk-swift.app/Contents/MacOS/slunk-swift",
      "args": ["--mcp"]
    }
  }
}

MCP Tools

The server exposes eight MCP tools that you can invoke through your MCP client to perform targeted Slack searches and data analysis.

Notes on privacy and storage

Real-time Slack monitoring is performed on your device with local storage in SQLite. Data retention and deduplication are handled automatically to keep your local dataset manageable.

Available tools

searchConversations

Natural language search across all messages in Slack conversations.

search_messages

Precise filtering by channel, user, or date to narrow results.

get_thread_context

Retrieve complete thread conversations for referenced messages.

get_message_context

Decode short messages and emojis to provide full context.

parse_natural_query

Extract user intent from natural language queries.

conversational_search

Support multi-turn search sessions for refinement and follow-up questions.

discover_patterns

Identify trending topics and patterns across Slack messages.

suggest_related

Suggest related conversations based on your query and history.