webex_mcp_server

webex_mcp_server

Enables Claude Desktop to send messages, manage spaces, and automate team collaboration in Cisco Webex Teams via the Model Context Protocol.

Category
Visit Server

README

Webex Teams MCP Server

A Model Context Protocol (MCP) server that enables Claude Desktop to interact with Cisco Webex Teams. Send messages, manage spaces, and automate team collaboration directly from Claude.

License Python

✨ Features

  • šŸš€ 11 Powerful Tools for complete Webex Teams integration
  • šŸ’¬ Messaging: Send, retrieve, and delete messages with Markdown support
  • šŸ‘„ Space Management: Create, search, and manage team spaces
  • šŸ¤ People Management: Add members, list participants, and get user details
  • šŸ”’ Secure: Uses official Webex Teams API with bot tokens
  • ⚔ Async: Built with async/await for optimal performance

šŸ“‹ Prerequisites

  • Python 3.10+ installed
  • Webex Teams Account (free at https://www.webex.com/)
  • Webex Bot Token or Personal Access Token
  • Claude Desktop installed

šŸš€ Quick Start

1. Get a Webex Bot Token

Option A: Create a Bot (Recommended for production)

  1. Go to https://developer.webex.com/my-apps/new/bot
  2. Fill in bot details and create the bot
  3. Copy the Bot Access Token immediately (you won't see it again!)
  4. Add the bot to your Webex spaces

Option B: Personal Access Token (For testing only)

  1. Go to https://developer.webex.com/docs/getting-started
  2. Your token is displayed after logging in
  3. āš ļø Warning: Personal tokens expire after 12 hours

2. Install

# Clone the repository
git clone https://github.com/YOUR_USERNAME/webex-mcp-server.git
cd webex-mcp-server

# Create and activate virtual environment (recommended)
python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

3. Configure Claude Desktop

Edit your Claude Desktop configuration file:

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

Add this configuration:

{
  "mcpServers": {
    "webex": {
      "command": "/FULL/PATH/TO/venv/bin/python",
      "args": [
        "/FULL/PATH/TO/webex-mcp-server/src/webex_mcp_server.py"
      ],
      "env": {
        "WEBEX_ACCESS_TOKEN": "YOUR_WEBEX_BOT_TOKEN_HERE"
      }
    }
  }
}

Important Notes:

  • Replace /FULL/PATH/TO/ with your actual absolute path
  • Replace YOUR_WEBEX_BOT_TOKEN_HERE with your actual token
  • On macOS, use /venv/bin/python
  • On Windows, use \venv\Scripts\python.exe

4. Restart Claude Desktop

Completely quit and restart Claude Desktop to load the MCP server.

5. Test It!

In Claude Desktop, try:

Can you list my Webex spaces?

You should see your Webex spaces listed! šŸŽ‰

šŸ› ļø Available Tools

Messaging

  • send_message - Send text or Markdown messages to spaces
  • get_messages - Retrieve conversation history
  • delete_message - Remove messages (with permissions)

Space Management

  • list_spaces - List all accessible spaces
  • get_space_details - Get detailed space information
  • create_space - Create new team spaces
  • search_spaces - Find spaces by name

People Management

  • add_person_to_space - Add members to spaces
  • list_space_members - List all space participants
  • get_person_details - Get user information
  • get_my_details - Get bot/user account info

šŸ’” Usage Examples

Send a Message

Send a message to my "Project Alpha" space saying "Meeting starts in 5 minutes!"

Create a Space

Create a new Webex space called "Q1 Planning" and add john@company.com as a member.

Get Space Messages

Show me the last 10 messages from my "Engineering Team" space.

Search for Spaces

Find all my Webex spaces that contain "customer" in the name.

šŸ”§ Advanced Configuration

Multiple MCP Servers

If you have other MCP servers (like Splunk), combine them:

{
  "mcpServers": {
    "webex": {
      "command": "/path/to/venv/bin/python",
      "args": ["/path/to/webex_mcp_server.py"],
      "env": {
        "WEBEX_ACCESS_TOKEN": "YOUR_TOKEN"
      }
    },
    "splunk": {
      "command": "node",
      "args": ["splunk-server.js"]
    }
  }
}

Environment Variables

Instead of putting the token in the config, use environment variables:

{
  "mcpServers": {
    "webex": {
      "command": "/path/to/venv/bin/python",
      "args": ["/path/to/webex_mcp_server.py"],
      "env": {
        "WEBEX_ACCESS_TOKEN": "${WEBEX_TOKEN}"
      }
    }
  }
}

Then set WEBEX_TOKEN in your system environment.

šŸ› Troubleshooting

"Server not found" in Claude Desktop

  1. Check that paths in claude_desktop_config.json are absolute (not relative)
  2. Verify the Python virtual environment path is correct
  3. Restart Claude Desktop completely (quit, don't just close window)

"Authentication failed" errors

  1. Verify your WEBEX_ACCESS_TOKEN is correct
  2. Check that the token hasn't expired (personal tokens expire in 12 hours)
  3. Ensure the bot has been added to spaces you're trying to access

"Permission denied" errors

  1. Bot tokens need to be added to spaces before they can interact
  2. Some operations require moderator permissions
  3. Check bot has necessary scopes in the Webex Developer portal

Connection test

Create a test script:

import os
from webexteamssdk import WebexTeamsAPI

token = os.getenv("WEBEX_ACCESS_TOKEN")
api = WebexTeamsAPI(access_token=token)

# Test connection
me = api.people.me()
print(f"āœ… Connected as: {me.displayName}")

# List spaces
rooms = list(api.rooms.list(max=5))
print(f"āœ… Found {len(rooms)} spaces")

šŸ—ļø Development

Project Structure

webex-mcp-server/
|── webex_mcp_server.py         # Main MCP server
ā”œā”€ā”€ requirements.txt            # Python dependencies
ā”œā”€ā”€ README.md                   # This file
ā”œā”€ā”€ LICENSE                     # MIT License

Running in Development

# Activate virtual environment
source venv/bin/activate

# Set token
export WEBEX_ACCESS_TOKEN="your_token_here"

# Run server directly
python src/webex_mcp_server.py

Adding New Tools

  1. Define the tool in list_tools()
  2. Create a handler function handle_your_tool(args)
  3. Add the handler to call_tool()

šŸ¤ Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/AmazingFeature)
  3. Commit your changes (git commit -m 'Add some AmazingFeature')
  4. Push to the branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

šŸ“ License

This project is licensed under the MIT License - see the LICENSE file for details.

šŸ”— Resources

šŸ™ Acknowledgments

šŸ“§ Support


Made with ā¤ļø for the Cisco community

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured