MCP AI Studio

MCP AI Studio

Connect, inspect, and operate any Streamable HTTP MCP server directly inside VS Code or Windsurf.

Install from Open VSX

What it does

MCP AI Studio embeds a full MCP client in an editor webview. Point it at any server URL, discover tools, run calls with generated forms, and inspect responses without leaving your editor.

  • Connect to any MCP server: enter any URL and restore it on next open.
  • Discover and call tools: input forms are auto-generated from JSON Schema.
  • Inspect responses: JSON output is formatted and copy-ready.

Quick start

  • Install the extension and open the MCP AI Studio workbench.
  • Open Configurator and set your MCP server URL.
  • Save and connect, then browse and call tools.
Typical URL: http://localhost:<port>/mcp or https://your-server.com/mcp

Configuration

Set values via Settings UI or settings.json. Workspace settings apply per project.

{
  "mcpAiStudio.serverUrl": "http://localhost:8080/mcp",
  "mcpAiStudio.title": "My Project Tools",
  "mcpAiStudio.subtitle": "Powered by Spring AI MCP",
  "mcpAiStudio.clientName": "my-project",
  "mcpAiStudio.clientVersion": "1.0.0"
}

Compatibility

Works with servers implementing MCP Streamable HTTP, including Spring AI MCP, FastMCP, Node SDK based servers, and any endpoint supporting tools/list and tools/call.

mcpAiStudio.serverUrlMCP server URL prefilled on open.
mcpAiStudio.titleTitle shown in the workbench header.
mcpAiStudio.clientNameClient name sent in MCP initialize handshake.