Skip to main content
MCP is an open standard for securely connecting AI assistants to external data sources and tools. In Zero Runtime AI Agents, attach MCP servers to auto-discover services, databases, and APIs. The agent picks and runs the right tools and turns results into natural responses.

How It Works

MCP tools are automatically discovered and made available to your agent, which intelligently chooses which tools to use based on user requests. When a user asks for information that requires external data, the agent will:
1

Identify the need

Detect that the user’s request requires external data.
2

Select tools

Choose the appropriate tools from the available MCP servers.
3

Execute

Run the tools with the relevant parameters.
4

Respond

Process the results and provide a natural language response.
This integration allows your voice agent to access real-time data and external services while maintaining a natural conversational flow.

Transport Methods

Zero Runtime supports two transport methods for MCP servers.

Example

Pass MCP servers to the agent via the mcp_servers parameter. Use MCPServerStdio for local scripts and MCPServerHTTP for remote services.
The agent auto-discovers every tool exposed by each server and chooses among them at runtime, so you don’t register tools individually.

Server options

MCPServerStdio (local process)

MCPServerHTTP (remote service)

The parameter names above are for the Python SDK. The JavaScript and Go SDKs use command + args (+ env) for STDIO and url + headers for HTTP. For example, MCPServerStdio('python', { args: [...] }) and MCPServerHTTP(url, { headers }) in JS, or &zrt.MCPServerStdio{Command, Args, Env} and &zrt.MCPServerHTTP{URL, Headers} in Go.

What’s Next

Function Tools

Add custom Python functions as tools.

RAG

Ground responses in a knowledge base.

References

Examples

MCP Client

Consume tools from an MCP server.

SDK Reference

MCP

MCP in the Python API reference.