# echelon-ai-labs/zoom-mcp architecture

> Architecture diagram of the GitHub repository echelon-ai-labs/zoom-mcp, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-09-27). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/echelon-ai-labs/zoom-mcp
- Repository: https://github.com/echelon-ai-labs/zoom-mcp

## Overview

##### Main Components
- CLI Entry Point
- `scripts/setup.sh`, `scripts/check_env.py`, `scripts/test_zoom_connection.py`
- `src/zoom_mcp/cli.py`
- MCP Server Core
- `src/zoom_mcp/server.py`
- Authentication Module
- `src/zoom_mcp/auth/zoom_auth.py`
- Resource Handlers
- `src/zoom_mcp/resources/recordings.py`
- (future: other `resources/*.py`)
- Utility Tools
- `src/zoom_mcp/tools/recordings.py`
- Configuration
- `.env` (populated from `.env.example`)
- `pyproject.toml` (dependencies & entry points)
- External Services
- Zoom OAuth2 endpoint
- Zoom REST API

##### Relationships & Data Flows
- User invokes CLI or directly starts the MCP server.
- CLI → MCP Server: parses arguments, passes control to `server.py`.
- MCP Server receives HTTP requests (from Claude or other clients).
- For each request:
a. Server calls Auth Module to acquire/refresh OAuth token.
b. Auth Module ↔ Zoom OAuth2 endpoint (Basic Auth → access token).
c. Server calls Resource Handlers, passing token.
d. Resource Handler ↔ Zoom REST API (e.g., GET /meetings, /recordings).
e. Utility Tools process or transform API payloads as needed.
- Server returns JSON responses to client.

##### Architectural Patterns & Principles
- Layered Design:
- Presentation Layer (CLI & HTTP API)
- Service Layer (`server.py` orchestrator)
- Integration Layer (Auth + Resources + Tools)
- Single Responsibility: each module does one thing (auth, resources, tools).
- Configuration‐driven: credentials in `.env`, tool behavior via CLI flags.
- Extensibility: new resources or tools can be added in `resources/` and `tools/`.

##### Capturing Essential Details
- `.env` loading by Auth Module.
- Token caching/renewal loop.
- How tests (`tests/test_zoom_auth.py`) simulate or mock Auth.
- Avoid unnecessary fragmentation—group closely related modules in one container.

## Diagram (Mermaid)

```mermaid
graph TB
    %% Presentation Layer
    subgraph "Presentation Layer"
        CLI_Scripts["scripts/setup.sh"]:::test
        CLI_Check["scripts/check_env.py"]:::test
        CLI_TestConn["scripts/test_zoom_connection.py"]:::test
        CLI_py["src/zoom_mcp/cli.py"]:::internal
    end

    %% MCP Server Core
    subgraph "MCP Server Core"
        Server["src/zoom_mcp/server.py"]:::internal
        subgraph "Integration Layer"
            Auth["src/zoom_mcp/auth/zoom_auth.py"]:::internal
            Resource["src/zoom_mcp/resources/recordings.py"]:::internal
            Tool["src/zoom_mcp/tools/recordings.py"]:::internal
        end
    end

    %% Configuration Store
    subgraph "Configuration Store"
        Env[".env"]:::config
        PyProj["pyproject.toml"]:::config
    end

    %% External Services
    subgraph "External Services"
        OAuth2["Zoom OAuth2 Endpoint"]:::external
        RESTAPI["Zoom REST API"]:::external
        Client["Client (e.g., Claude)"]:::external
    end

    %% Authentication Tests
    TestAuth["tests/test_zoom_auth.py"]:::test

    %% Data Flows
    CLI_py -->|"parse args / start"| Server
    CLI_Scripts -.-> Server
    CLI_Check -.-> Server
    CLI_TestConn -.-> Server

    Server -->|"load config"| Env
    Server -->|"load config"| PyProj

    Server -->|"Acquire Token"| Auth
    Auth -->|"Basic Auth"| OAuth2
    OAuth2 -->|"Token"| Auth
    Auth -->|"return token"| Server

    Server -->|"API call"| Resource
    Resource -->|"GET /recordings"| RESTAPI
    RESTAPI -->|"payload"| Resource
    Resource -->|"processed"| Server

    Server -->|"util transform"| Tool
    Tool -->|"transformed data"| Server

    Server -->|"HTTP response"| Client

    TestAuth -->|"mock token"| Auth

    %% Click Events
    click CLI_Scripts "https://github.com/echelon-ai-labs/zoom-mcp/blob/main/scripts/setup.sh"
    click CLI_Check "https://github.com/echelon-ai-labs/zoom-mcp/blob/main/scripts/check_env.py"
    click CLI_TestConn "https://github.com/echelon-ai-labs/zoom-mcp/blob/main/scripts/test_zoom_connection.py"
    click CLI_py "https://github.com/echelon-ai-labs/zoom-mcp/blob/main/src/zoom_mcp/cli.py"
    click Server "https://github.com/echelon-ai-labs/zoom-mcp/blob/main/src/zoom_mcp/server.py"
    click Auth "https://github.com/echelon-ai-labs/zoom-mcp/blob/main/src/zoom_mcp/auth/zoom_auth.py"
    click Resource "https://github.com/echelon-ai-labs/zoom-mcp/blob/main/src/zoom_mcp/resources/recordings.py"
    click Tool "https://github.com/echelon-ai-labs/zoom-mcp/blob/main/src/zoom_mcp/tools/recordings.py"
    click Env "https://github.com/echelon-ai-labs/zoom-mcp/blob/main/.env.example"
    click PyProj "https://github.com/echelon-ai-labs/zoom-mcp/blob/main/pyproject.toml"
    click TestAuth "https://github.com/echelon-ai-labs/zoom-mcp/blob/main/tests/test_zoom_auth.py"

    %% Styles
    classDef internal fill:#D6EFFF,stroke:#000;
    classDef config fill:#E0FFD6,stroke:#000;
    classDef external fill:#FFE4B3,stroke:#000;
    classDef test stroke-dasharray:5 5,fill:#fff;
```
