webex-messaging
A Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to Cisco Webex messaging capabilities.
claude mcp add --transport stdio kashyap-ai-ml-solutions-webex-messaging-mcp-server node mcpServer.js \ --env PORT="3001" \ --env MCP_MODE="stdio or http" \ --env WEBEX_USER_EMAIL="your_email@example.com" \ --env WEBEX_API_BASE_URL="https://webexapis.com/v1" \ --env WEBEX_PUBLIC_WORKSPACE_API_KEY="your_token_here"
How to use
The Webex MCP Server provides AI assistants with full access to Cisco Webex messaging capabilities through a modular, tool-based interface. It exposes a suite of 52 tools organized into categories such as Messages, Rooms, Teams, Memberships, People, Webhooks, and Enterprise, enabling actions like creating and listing messages, managing rooms, handling memberships, and configuring webhooks. The server supports two transport modes: STDIO (default) for direct integration with local tooling and HTTP (StreamableHTTP) for network-based clients. Use the included tool discovery commands to understand available capabilities and test endpoints via the MCP HTTP endpoint or STDIO interactions. The server is TypeScript/JavaScript implemented with robust error handling and enterprise-ready authentication support.
How to install
Prerequisites:
- Node.js 18+ (20+ recommended)
- npm (bundled with Node.js)
- Optional: Docker if you prefer containerized deployment
Installation steps:
-
Clone the repository: git clone <repository-url> cd webex-messaging-mcp-server
-
Install dependencies: npm install
-
Configure environment: cp .env.example .env
Edit .env with your Webex API token and related settings
-
Run the server (STDIO mode): node mcpServer.js
-
Run the server in HTTP mode (if desired): npm run start:http
-
Validate installation:
- List tools: node index.js tools
- Discover tools: npm run discover-tools
- Access MCP endpoint (HTTP mode): http://localhost:3001/mcp
Notes:
- Ensure WEBEX_PUBLIC_WORKSPACE_API_KEY is set without the Bearer prefix.
- If you use a lower Node.js version, consider adding node-fetch and adapting tools to use fetch.
Additional notes
Tips and common considerations:
- Token renewal: Webex tokens are short-lived. Update WEBEX_PUBLIC_WORKSPACE_API_KEY when tokens expire.
- Environment variables: Use the provided .env file to override defaults; ensure required ones are set (WEBEX_PUBLIC_WORKSPACE_API_KEY).
- Transport mode: MCP_MODE can be 'stdio' (default) or 'http'; in HTTP mode the server exposes health and MCP endpoints as described in the docs.
- CORS and SSE: In HTTP mode, the server supports proper CORS configuration and Server-Sent Events for streaming responses.
- Docker: If deploying via Docker, build and run per the Docker usage section in the README; ensure environment variables are passed via --env-file or env options.
- Node version considerations: If using an older Node.js version, fetch may be unavailable; install and configure node-fetch as needed and ensure imports provide a fetch alias.
Related MCP Servers
any-chat-completions
MCP Server for using any LLM as a Tool
bitbucket
Bitbucket MCP - A Model Context Protocol (MCP) server for integrating with Bitbucket Cloud and Server APIs
time
⏰ Time MCP Server: Giving LLMs Time Awareness Capabilities
unity-editor
An MCP server and client for LLMs to interact with Unity Projects
website-publisher
AI Website builder and publisher MCP. Quickly publish and deploy your AI generated code as real website URL. Support html, css, js, python etc.
xgmem
Global Memory MCP server, that manage all projects data.