What does the `getSecretPassphrase` tool return?
It returns a random US State and its signature soup combination, for example “New England Clam Chowder” or “Texas Chili”.
@gbti-network
基本信息
Example node MCP server. When a user asks the agent for the passphrase, a special code phase is provided.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-basic-test": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"--",
"node",
"index.js"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
Super Secret MCP Server is a Model Context Protocol (MCP) server implemented in pure Node.js. It provides a single fun tool that generates random combinations of a US State and its signature soup (e.g., “Louisiana Gumbo”). It is intended for developers and users who want to test MCP integration or add a whimsical secret‑passphrase feature to their AI assistants.
Clone the repository, install dependencies with npm install, then start the server with npx @modelcontextprotocol/inspector -- node index.js. The server runs over STDIO transport and exposes the getSecretPassphrase tool. In Cascade (Windsurf), configure the server by adding an entry to the mcp_config.json file with the appropriate command and arguments.
getSecretPassphrase with schema validationIt returns a random US State and its signature soup combination, for example “New England Clam Chowder” or “Texas Chili”.
Node.js (latest LTS version recommended) is required. The server runs with standard Node.js and does not need additional global packages beyond those installed via `npm install`.
Use the MCP Inspector: start the server with `npx @modelcontextprotocol/inspector -- node index.js`, then list tools and test the `getSecretPassphrase` tool.
Add an entry to your `mcp_config.json` with the command `npx`, arguments including `--yes node <path-to-project>/index.js`, and auto‑approve `getSecretPassphrase`. Place the config file at `%USERPROFILE%\.codeium\windsurf\mcp_config.json` (Windows) or `$HOME/.codeium/windsurf/mcp_config.json` (macOS/Linux).
Logs are written to the `.logs` directory in the project root, using the custom logging system.

Give an agent a place to put large output. Instead of returning 40k characters of a build log into the conversation, it posts the file to DocBin and hands back one short URL. Docs render with syntax highlighting and mark
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

评论