MCP (Model Context Protocol) is an open protocol that lets AI models connect to external tools, data sources, and applications in a standardized way.
A useful analogy is that MCP is to AI what HTTP is to web browsers: a common language for communication.
There are typically three parts:
MCP Client
The AI application or assistant.
Requests information or actions.
MCP Server
Exposes data and tools to the AI.
Acts as a bridge between the AI and your systems.
Resources and Tools
Data the AI can read (documents, databases, files).
Actions the AI can perform (create tickets, update records, send messages).
Prerequisites
Before connecting your AI agent, ensure that:
You have access to a Zeevou account.
MCP access has been enabled for your account.
Your AI agent or client supports the Model Context Protocol (MCP).
Connection Steps
1. Obtain an Access Token
To obtain an access token, contact Zeevou Support and request OAuth 2.0 client credentials.
You will receive:
Client ID
Client Secret
Use these credentials to obtain an OAuth 2.0 access token, which will be used to authenticate requests to the Zeevou MCP Server.
2. Configure Your AI Agent
Add the Zeevou MCP server to your AI agent's MCP configuration and pass your access token as an Authorization header.
3. Verify the Connection
After configuration:
Restart or reload your AI agent.
Confirm that the Zeevou MCP server appears in the list of available MCP servers.
Verify that the available Zeevou tools can be discovered successfully.
Authentication
The Zeevou MCP Server uses bearer token authentication.
All requests must include the following HTTP header:
Authorization: Bearer YOUR_ACCESS_TOKEN
If your access token expires or becomes invalid, obtain a new access token and update your MCP configuration.
