Skip to content

Slack MCP Server Usage Guide

Overview

This guide shows how to use the Slack MCP Server with different MCP clients and integration methods.

Tool Discovery

# Start interactive mode
mcp_platform interactive

# List available tools
mcpp> tools slack

# Discover tools using CLI
mcp_platform tools slack

from mcp_platform.client import MCPClient

async def discover_tools():
    client = MCPClient()
    tools = client.list_tools("slack")
    for tool in tools:
        print(f"Tool: {tool['name']} - {tool['description']}")

Available Tools

This template uses an external MCP server implementation. Tools are dynamically discovered at runtime.

Use the tool discovery methods above to see the full list of available tools for this template.

Usage Examples

# Start interactive mode
mcp_platform interactive

# Deploy the template (if not already deployed)
mcpp> deploy slack

# List available tools after deployment
mcpp> tools slack

Example tool calls (replace with actual tool names discovered above):

# Example - replace 'tool_name' with actual tool from discovery
mcpp> call slack tool_name '{"param": "value"}'

# Deploy the template
mcp_platform deploy slack

# Check deployment status
mcp_platform status

# View logs
mcp_platform logs slack

# Stop the template
mcp_platform stop slack

import asyncio
from mcp_platform.client import MCPClient

async def use_slack():
    client = MCPClient()

    # Start the server
    deployment = client.start_server("slack", {})

    if deployment["success"]:
        deployment_id = deployment["deployment_id"]

        try:
            # Discover available tools
            tools = client.list_tools("slack")
            print(f"Available tools: {[t['name'] for t in tools]}")

            # Example tool call (replace with actual tool name)
            # result = client.call_tool("slack", "tool_name", {"param": "value"})
            # print(f"Tool result: {result}")

        finally:
            # Clean up
            client.stop_server(deployment_id)
    else:
        print("Failed to start server")

# Run the example
asyncio.run(use_slack())

Integration Examples

Add this configuration to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "slack": {
      "command": "python",
      "args": ["-m", "mcp_platform", "connect", "slack", "--stdio"],
      "env": {
        "LOG_LEVEL": "info"
      }
    }
  }
}

Install the MCP extension and add this to your VS Code settings (.vscode/settings.json):

{
  "mcp.servers": {
    "slack": {
      "command": "python",
      "args": ["-m", "mcp_platform", "connect", "slack", "--stdio"],
      "env": {
        "LOG_LEVEL": "info"
      }
    }
  }
}

# Get connection details for other integrations
mcp_platform connect slack --llm claude
mcp_platform connect slack --llm vscode

Configuration

For template-specific configuration options, see the main template documentation. Common configuration methods:

# Deploy with environment variables
mcp_platform deploy slack --env KEY=VALUE

# Deploy with configuration
mcp_platform deploy slack --config key=value

# Deploy with nested configuration
mcp_platform deploy slack --config category__property=value

# Deploy with config file
mcp_platform deploy slack --config-file config.json

Troubleshooting

Common Issues

  1. Template not found: Ensure the template name is correct 

    mcp_platform list  # List available templates

  2. Connection issues: Check if the server is running 

    mcp_platform status

  3. Tool discovery fails: Try refreshing the tool cache 

    mcpp> tools slack --refresh

Debug Mode

Enable debug logging for troubleshooting:

# Interactive CLI with debug
LOG_LEVEL=debug mcp_platform interactive

# Deploy with debug logging
mcp_platform deploy slack --config log_level=debug

For more help, see the main documentation or open an issue in the repository.