home / mcp / zoom api mcp server
MCP Server generated by mcp.ag2.ai
Configuration
View docs{
"mcpServers": {
"ag2-mcp-servers-zoom-api": {
"command": "python",
"args": [
"mcp_server/main.py",
"stdio"
],
"env": {
"CONFIG": "{\\\"server\\\":\\\"zoom\\\"}",
"SECURITY": "{\\\"API_KEY\\\":\\\"YOUR_API_KEY\\\"}",
"CONFIG_PATH": "mcp_server/mcp_config.json"
}
}
}
}You run an MCP (Model Context Protocol) server that exposes Zoom’s API as a structured, programmable endpoint. This enables clients to discover, query, and interact with Zoom data through a consistent MCP interface, with tooling for development, testing, and deployment.
You connect an MCP client to the Zoom API MCP Server to access Zoom data through the MCP protocol. Use the stdio transport configuration when you run the server locally. The server exposes supported capabilities described by the underlying OpenAPI spec and provides command-line and environment-based configuration to tailor security and where the server reads its config.
Prerequisites: Python 3.9 or newer, pip, and uv for running the server in development or production modes.
Step 1: Prepare the environment and dependencies.
# Ensure Python 3.9+ is installed
python --version
# Ensure pip is available
pip --versionStep 2: Clone the project repository and enter the project directory.
git clone <repository-url>
cd mcp-serverStep 3: Install development dependencies. You can use the dedicated setup script or install manually.
pip install -e ".[dev]"
```
# Alternative using uv if you prefer it for development
```sh
uv pip install --editable ".[dev]"Step 4: Run the MCP server in stdio mode to start serving MCP requests from your local environment.
python mcp_server/main.py stdioStep 5: Configure runtime parameters via environment variables if needed.
# Example environment variables you can set
export CONFIG_PATH=mcp_server/mcp_config.json
export CONFIG={"server":"zoom"}
export SECURITY={"API_KEY":"your-api-key"}Configuration notes you may encounter involve pointing the server at a JSON configuration file or passing a JSON string with configuration details. You can also supply security parameters to protect MCP access.
Development and quality tooling are used to maintain code health and reliability, including linting, static analysis, and tests.
The server supports running via a local stdio command. The explicit command to start the server is shown below, along with the environment variables you may provide to control its runtime behavior.
{
"mcpServers": [
{
"type": "stdio",
"name": "zoom_api_mcp",
"command": "python",
"args": ["mcp_server/main.py", "stdio"],
"env": [
{"name": "CONFIG_PATH", "value": "mcp_server/mcp_config.json"},
{"name": "CONFIG", "value": "{\"server\":\"zoom\"}"},
{"name": "SECURITY", "value": "{\"API_KEY\":\"YOUR_API_KEY\"}"}
]
}
]
}The runtime accepts several environment variables to customize behavior. Common examples include CONFIG_PATH for a local JSON configuration file, CONFIG for an inline JSON configuration, and SECURITY for security-related settings such as API keys.
If you need to adjust the server’s behavior, provide a JSON configuration file or inline JSON via the CONFIG_PATH or CONFIG variables, and supply any required security keys through SECURITY.
Ruff linting and formatting to ensure clean, consistent code across the project.
Static analysis using mypy, bandit, and semgrep to catch type issues and security concerns.
Pytest-based test suite with coverage reports to validate MCP endpoints and server behavior.
Pre-commit hooks to enforce code quality before commits.
Hatch-based build process for packaging and publishing the MCP server.