MCP

SUPERWISE® publishes two Model Context Protocol (MCP) servers that let AI-powered code editors (Cursor, Windsurf, Claude Desktop, Claude Code, etc.) talk directly to our platform and to our documentation.

What is MCP?

Model Context Protocol (MCP) is an open standard that allows AI applications to securely access external data sources and tools. The SUPERWISE® Docs: Runtime Agentic AI Governance & Operations MCP server provides AI agents with:

Direct API access to SUPERWISE® Docs: Runtime Agentic AI Governance & Operations functionality
Documentation search capabilities
Real-time data from your SUPERWISE® Docs: Runtime Agentic AI Governance & Operations account
Code generation assistance for SUPERWISE® Docs: Runtime Agentic AI Governance & Operations integrations

Available servers

Server	URL	Best for
SUPERWISE® Docs: API & User Guides	`https://docs.superwise.ai/mcp`	Calling the REST API, searching user guides, reading real-time account data, generating HTTP-based integration code.
SUPERWISE® Python SDK Reference	`https://mcp.sdk.docs.superwise.ai/mcp`	Writing Python code with the `superwise_api` package — classes, methods, schemas, Quickstart examples.

Both servers speak streamable HTTP MCP and need no auth to read the public docs. The API server additionally passes your credentials through for authenticated requests on your behalf.

Which one should I use?

Most editors can register multiple MCP servers at once — keep both enabled and your editor will pick the right one per question. A rough guide:

Writing Python (import superwise_api, pip install superwise_api, class and schema reference) → Python SDK Reference server.
Calling REST endpoints, generating curl examples, or asking about product concepts (policies, dashboards, agents, guardrails) → API & User Guides server.

Setup

SUPERWISE® Docs: REST API & User Guides

SUPERWISE® Docs: Runtime Agentic AI Governance & Operations hosts a remote MCP server at https://docs.superwise.ai/mcp. Configure your AI development tools to connect to this server. If your APIs require authentication, you can pass in headers via query parameters or however headers are configured in your MCP client.

Add to~/.cursor/mcp.json:

{
  "mcpServers": {
    "ptp": {
      "url": "https://docs.superwise.ai/mcp"
    }
  }
}

SUPERWISE® Python SDK Reference

Add to~/.cursor/mcp.json:

{
  "mcpServers": {
    "superwise-sdk-docs": {
      "url": "https://mcp.sdk.docs.superwise.ai/mcp"
    }
  }
}

Testing Your MCP Setup

Once configured, you can test your MCP server connection:

Open your AI editor (Cursor, Windsurf, etc.)
Start a new chat with the AI assistant
Ask about SUPERWISE® Docs or SDK - try questions like:
- "Using the SUPERWISE Python SDK, show me how to create a Policy."
- "List the available Dashboard methods in superwise_api."
- "Using the SUPERWISE REST API, how do I POST a new agent?"

The AI should now have access to your SUPERWISE® Docs: Runtime Agentic AI Governance & Operations account data and documentation through the MCP server.