MCP servers¶
This topic describes how to extend the Cortex Code Agent SDK with external MCP (Model Context Protocol) servers.
MCP servers let your agent call external tools alongside built-in tools like Read, Edit, and Bash.
Overview¶
The current Cortex runtime supports external MCP servers over these transports:
stdiohttpsse
Connecting external MCP servers¶
Stdio servers¶
Stdio servers are external processes that communicate over standard input and output.
HTTP and SSE servers¶
For remote MCP servers that communicate over HTTP or Server-Sent Events (SSE):
You can also use "type": "sse" for servers that use SSE transport.
Controlling which MCP tools are allowed¶
MCP tools are namespaced with the mcp__ prefix in the format mcp__<server-name>__<tool-name>. Use the
allowedTools (TypeScript) or allowed_tools (Python) option to control which tools the agent can call:
You can also use disallowedTools / disallowed_tools to block specific tools.
Disabling MCP¶
To disable all MCP servers for a session, use the noMcp (TypeScript) or no_mcp (Python) option:
Feature comparison¶
Feature |
Python |
TypeScript |
|---|---|---|
External MCP servers (stdio) |
Yes ( |
Yes ( |
External MCP servers (HTTP/SSE) |
Yes ( |
Yes ( |
|
Yes |
Yes |
|
Yes |
Yes |
Legal notices¶
Where your configuration of Cortex Code uses a model provided on the Model and Service Pass-Through Terms, your use of that model is further subject to the terms for that model on that page.
The data classification of inputs and outputs are as set forth in the following table.
Input data classification |
Output data classification |
Designation |
|---|---|---|
Usage Data |
Customer Data |
Covered AI Features [1] |
For additional information, refer to Snowflake AI and ML.