Model Context Protocol (MCP)
MCP (Model Context Protocol) is a protocol that enables LLMs to access custom tools and services. An MCP client (Cascade, in this case) can make requests to MCP servers to access tools that they provide. Cascade now natively integrates with MCP, allowing you to bring your own selection of MCP servers for Cascade to use. See the official MCP docs for more information.
Adding a new MCP plugin
New MCP plugins can be added by going to the Settings
> Tools
> Windsurf Settings
> Add Server
section.
If you cannot find your desired MCP plugin, you can add it manually by clicking View Raw Config
button and editing the raw mcp_config.json
file.
When you click on an MCP server, simply click + Add Server
to expose the server and its tools to Cascade.
Cascade supports two transport types for MCP servers: stdio
and /sse
.
For /sse
servers, the URL should reflect that of the endpoint and resemble https://<your-server-url>/sse
.
mcp_config.json
The ~/.codeium/mcp_config.json
file is a JSON file that contains a list of servers that Cascade can connect to.
The JSON should follow the same schema as the config file for Claude Desktop.
Here’s an example configuration, which sets up a single server for Google Maps:
Be sure to provide the required arguments and environment variables for the servers that you want to use.
See the official MCP server reference repository or OpenTools for some example servers.
Notes
- Since MCP tool calls can invoke code written by arbitrary server implementers, we do not assume liability for MCP tool call failures. To reiterate:
- We currently only support tools, not prompts nor resources. In other words, Cascade will be able to request and use a server’s tools, but not the other endpoints that a server exposes.