MCP Apps

Render interactive UI components from MCP servers directly in your chat interface.

"""ADK agent backing the MCP Apps demo.

This agent has no bespoke backend tools — the CopilotKit Next.js runtime is
wired with ``mcpApps: { servers: [...] }`` (see
``src/app/api/copilotkit-mcp-apps/route.ts``), which auto-applies the MCP
Apps middleware. The middleware exposes the remote MCP server's tools to
this agent at request time and emits the activity events that CopilotKit's
built-in ``MCPAppsActivityRenderer`` renders inline in the chat.

Reference:
https://docs.copilotkit.ai/integrations/langgraph/generative-ui/mcp-apps
"""

from __future__ import annotations

from ag_ui_adk import AGUIToolset
from google.adk.agents import LlmAgent

from agents.shared_chat import get_model, stop_on_terminal_text

_INSTRUCTION = """\
You draw simple diagrams in Excalidraw via the MCP tool.

SPEED MATTERS. Produce a correct-enough diagram fast; do not optimize
for polish. Target: one tool call, done in seconds.

When the user asks for a diagram:
1. Call `create_view` ONCE with 3-5 elements total: shapes + arrows +
   an optional title text.
2. Use straightforward shapes (rectangle, ellipse, diamond) with plain
   `label` fields (`{"text": "...", "fontSize": 18}`) on them.
3. Connect with arrows. Endpoints can be element centers or simple
   coordinates — you don't need edge anchors / fixedPoint bindings.
4. Include ONE `cameraUpdate` at the END of the elements array that
   frames the whole diagram. Use an approved 4:3 size (600x450 or
   800x600). No opening camera needed.
5. Reply with ONE short sentence describing what you drew.

Every element needs a unique string `id` (e.g. `"b1"`, `"a1"`,
`"title"`). Standard sizes: rectangles 160x70, ellipses/diamonds
120x80, 40-80px gap between shapes.

Do NOT:
- Call `read_me`. You already know the basic shape API.
- Make multiple `create_view` calls.
- Iterate or refine. Ship on the first shot.
- Add decorative colors / fills / zone backgrounds unless the user
  explicitly asks for them.
- Add labels on arrows unless crucial.

If the user asks for something specific (colors, more elements,
particular layout), follow their lead — but still in ONE call.
"""

mcp_apps_agent = LlmAgent(
    name="McpAppsAgent",
    model=get_model(),
    instruction=_INSTRUCTION,
    tools=[AGUIToolset()],
    after_model_callback=stop_on_terminal_text,
)

What is this?#

MCP Apps are MCP servers that expose tools with associated UI resources. When the agent calls one of these tools, CopilotKit automatically fetches the resource and renders the UI component in the chat; no additional frontend code required.

Free course: See this pattern built end-to-end in Build Interactive Agents with Generative UI — a free DeepLearning.AI short course taught by CopilotKit's CEO covering the full Generative UI spectrum (Controlled, Declarative, and Open-Ended).

Key benefits:

Zero frontend code — UI components are served by the MCP server
Full interactivity — components can use HTML, CSS, and JavaScript
Secure sandboxing — content runs in isolated iframes
Thread persistence — MCP Apps are stored in conversation history and restored on reconnect

Wire the runtime to your MCP server(s)#

A single mcpApps.servers entry on the runtime is all it takes. The runtime auto-applies the MCP Apps middleware to every registered agent: each time an agent calls a tool backed by an MCP UI resource, the middleware fetches the resource and emits an activity event that the built-in MCPAppsActivityRenderer renders inline in the chat as a sandboxed iframe.

route.ts

// The `mcpApps.servers` config is all you need server-side. The runtime// auto-applies the MCP Apps middleware to every registered agent: on each// MCP tool call it fetches the associated UI resource and emits an// `activity` event that the built-in `MCPAppsActivityRenderer` renders// inline in the chat.const runtime = new CopilotRuntime({  // @ts-expect-error -- Published CopilotRuntime agents type wraps Record in  // MaybePromise<NonEmptyRecord<...>> which rejects plain Records;  // fixed in source, pending release.  agents: {    "mcp-apps": mcpAppsAgent,    "headless-complete": headlessCompleteAgent,  },  mcpApps: {    servers: [      {        type: "http",        url: process.env.MCP_SERVER_URL || "https://mcp.excalidraw.com",        // Always pin a stable `serverId`. Without it CopilotKit hashes the        // URL, and a URL change silently breaks restoration of persisted        // MCP Apps in prior conversation threads.        serverId: "excalidraw",      },    ],  },});

Always pin a serverId

In production, always provide a stable serverId. Without it, CopilotKit hashes the server URL, and a URL change (for example between environments) silently breaks restoration of MCP Apps persisted in earlier conversation threads.

No frontend renderer needed#

Unlike custom activity types, the MCP Apps renderer is already registered by CopilotKit out of the box. A plain <CopilotChat /> is enough; no renderActivityMessages prop, no manual useRenderActivityMessage wiring.

page.tsx

  // No `renderActivityMessages`, no `useRenderActivityMessage` — the  // CopilotKitProvider auto-registers the built-in `MCPAppsActivityRenderer`  // for the "mcp-apps" activity type. A plain <CopilotChat /> is enough.  return (    <CopilotKit runtimeUrl="/api/copilotkit-mcp-apps" agent="mcp-apps">      <div className="flex justify-center items-center h-screen w-full">        <div className="h-full w-full max-w-4xl">          <Chat />        </div>      </div>    </CopilotKit>  );

Transport types#

The middleware supports two transport types:

HTTP#

Use this format to connect to an MCP server that accepts standard HTTP requests:

{
  type: "http",
  url: "http://localhost:3101/mcp",
  serverId: "my-http-server"
}

SSE#

Use this format to connect to an MCP server that streams events over a persistent connection:

{
  type: "sse",
  url: "https://mcp.example.com/sse",
  headers: {
    "Authorization": "Bearer token"
  },
  serverId: "my-sse-server"
}

Example MCP servers#

Try these open-source MCP Apps servers to get started:

Excalidraw — collaborative whiteboard rendered in-chat
modelcontextprotocol/ext-apps — canonical reference implementations