Used as the runtime environment for the MCP server, enabling execution of the TypeScript code and providing build capabilities for creating a compiled executable.
Provides tools for accessing Slack's search functionality, allowing users to retrieve workspace information (users, channels), fetch messages from specific channels, get thread replies, and search through messages across the workspace.
Slack Search MCP Server
A Model Context Protocol (MCP) server that provides tools and resources to access Slack's search functionality. This server allows LLMs to search and retrieve users, channels, messages, and more from a Slack workspace.
Features
Tools
get_users- Get a list of users in the Slack workspaceget_channels- Get a list of channels in the Slack workspaceget_channel_messages- Get messages from a specific channelget_thread_replies- Get replies in a threadsearch_messages- Search for messages in Slack
Resources
allusers://- Get all users in the Slack workspaceallchannels://- Get all channels in the Slack workspace
Related MCP server: mcp-llm
Requirements
Bun runtime
Slack API token with appropriate permissions
Installation
Clone the repository
Install dependencies:
bun install
Usage
Set the Slack API token as an environment variable:
export SLACK_TOKEN=xoxb-your-token-hereRun the server:
bun run index.tsOr use the compiled version:
./dist/slack_search_function_mcp
Building
To build the executable:
This will create a compiled executable in the dist directory.
MCP Configuration
To use this server with an MCP-enabled LLM, add it to your MCP configuration:
Tool Examples
Get Users
Get Channels
Get Channel Messages
Get Thread Replies
Search Messages
Resource Examples
Get All Users
Get All Channels
Error Handling
The server includes comprehensive error handling for:
Invalid or missing Slack API token
API rate limits
Network errors
Invalid parameters
Authentication failures
Security
The Slack API token is never logged or exposed in responses
The token is securely passed via environment variables