Server SDK (Python)

The Server SDK is a Python library that enhances your existing AI agents with platform capabilities. Whether you’ve built your agent with LangGraph, CrewAI, or custom logic, the SDK connects it to the Agent Stack platform, giving you instant access to runtime-configurable services, interactive UI components, and deployment infrastructure. Built on top of the Agent2Agent Protocol (A2A), the SDK wraps your agent implementation and adds powerful functionality through A2A extensions. This enables your agent to leverage platform services like LLM providers, file storage, vector databases, and rich UI components. That’s all without rewriting your core agent logic.

What the SDK Provides

Feature	Purpose
Server wrapper	Simplified server creation and agent registration
Convenience wrappers	Simplified message types like `AgentMessage` that reduce boilerplate
Context management	Built-in conversation history and state management
Async generator pattern	Natural task-based execution with pause/resume capabilities
Dependency Injection Extensions	Dependency injection for LLM service, RAG embeddings, file storage and MCP integration
UI Extensions	Enables advanced interactive components including forms, citations and trajectory

Server Wrapper Example

Here we show server creation and agent registration:

# Copyright 2025 © BeeAI a Series of LF Projects, LLC
# SPDX-License-Identifier: Apache-2.0

import os

from a2a.types import Message
from agentstack_sdk.a2a.types import AgentMessage
from agentstack_sdk.server import Server
from agentstack_sdk.server.context import RunContext

server = Server()


@server.agent()
async def server_wrapper_example(input: Message, context: RunContext):
    """Your agent implementation"""
    yield AgentMessage(text="Hello from my agent!")


def run():
    server.run(host=os.getenv("HOST", "127.0.0.1"), port=int(os.getenv("PORT", 8000)))


if __name__ == "__main__":
    run()

The SDK uses a server-based architecture where you:

Create a Server instance and
Register your agent function

Advanced Server SDK Example

Here’s an example that incorporates multiple Server SDK capabilities:

# Copyright 2025 © BeeAI a Series of LF Projects, LLC
# SPDX-License-Identifier: Apache-2.0

import os
from typing import Annotated

from a2a.types import Message
from agentstack_sdk.a2a.extensions import (
    FormRender,
    TextField,
    FormRequestExtensionServer,
    FormRequestExtensionSpec,
)
from agentstack_sdk.a2a.types import AgentMessage
from agentstack_sdk.server import Server
from agentstack_sdk.server.context import RunContext
from pydantic import BaseModel

server = Server()


class UserDetails(BaseModel):
    name: str | None
    email: str | None


@server.agent()
async def advanced_server_wrapper_example(
    input: Message, context: RunContext, form_request: Annotated[FormRequestExtensionServer, FormRequestExtensionSpec()]
):
    """Agent that pauses execution to request user input"""
    yield AgentMessage(text="I need some information from you.")

    # Execution pauses here - task enters input_required state
    # User fills out the form in the UI
    form_data = await form_request.request_form(
        form=FormRender(
            title="Please provide your details",
            fields=[
                TextField(id="name", label="Your Name"),
                TextField(id="email", label="Email Address"),
            ],
        ),
        model=UserDetails,
    )

    # Execution resumes after user submits the form
    if form_data:
        yield AgentMessage(text=f"Thank you, {form_data.name}! I'll contact you at {form_data.email}.")
    else:
        yield AgentMessage(text="Form was not filled out.")


def run():
    server.run(host=os.getenv("HOST", "127.0.0.1"), port=int(os.getenv("PORT", 8000)))


if __name__ == "__main__":
    run()

Use the Asynchronous Generator Pattern to await the form request and pause the task while the user completes the form.
UI Extensions are used to create the forms and add the metadata to messages.

Asynchronous Generator Pattern

Agent functions are asynchronous generators that yield responses. This pattern aligns with A2A’s task model:

One function execution = One A2A task
Yielding data = Sending messages to the client
Pausing execution = Waiting for user input

The generator pattern is particularly powerful when your agent needs to request structured input from users. When you await a form request, execution pauses the task, allowing the user to fill out the form. Once submitted, execution resumes with the form data. The generator pattern enables agents to:

Stream responses incrementally
Yield multiple messages during a single task
Handle long-running operations gracefully

Extension System

Agent Stack utilizes A2A extensions to extend the protocol with Agent Stack-specific capabilities. They enable your agent to access platform services and enhance the user interface beyond what the base A2A protocol provides. There are two types of extensions:

UI Extensions

UI extensions add extra metadata to messages, enabling the Agent Stack UI to render more advanced interactive components:

Forms: Collect structured user input through interactive forms
Citations: Display source references with clickable inline links
Trajectory: Visualize agent reasoning steps with execution traces

These extensions enhance messages with metadata that the UI interprets to create rich, interactive experiences beyond standard text responses.

Dependency Injection Service Extensions

Service extensions use a dependency injection pattern where each run of the agent declares a demand that must be fulfilled by the client (consumer). The platform provides configured access to external services based on these demands:

LLM Service: Language model access with automatic provider selection
Embedding Service: Text embedding generation for RAG
Platform API: File storage, vector databases, and platform services
MCP: Model Context Protocol integration

# Copyright 2025 © BeeAI a Series of LF Projects, LLC
# SPDX-License-Identifier: Apache-2.0

import os
from typing import Annotated

from a2a.types import Message
from agentstack_sdk.a2a.extensions import LLMServiceExtensionServer, LLMServiceExtensionSpec
from agentstack_sdk.a2a.types import AgentMessage
from agentstack_sdk.server import Server
from agentstack_sdk.server.context import RunContext

server = Server()


@server.agent()
async def dependency_injection_example(
    input: Message,
    context: RunContext,
    llm: Annotated[LLMServiceExtensionServer, LLMServiceExtensionSpec.single_demand()],
):
    # The demand is fulfilled by the client - llm is provided if available
    if llm:
        # response = await llm.chat(messages=[...])
        # ...
        yield AgentMessage(text="LLM service is available.")
    else:
        yield AgentMessage(text="LLM service not available")


def run():
    server.run(host=os.getenv("HOST", "127.0.0.1"), port=int(os.getenv("PORT", 8000)))


if __name__ == "__main__":
    run()

Introduction

Deploy Agents

Agent Integration

Reference

Deploy Agent Stack

Custom UI Integration

Experimental

Community

What the SDK Provides

Server Wrapper Example

Advanced Server SDK Example

Asynchronous Generator Pattern

Extension System

UI Extensions

Dependency Injection Service Extensions

​What the SDK Provides

​Server Wrapper Example

​Advanced Server SDK Example

​Asynchronous Generator Pattern

​Extension System

​UI Extensions

​Dependency Injection Service Extensions

What the SDK Provides

Server Wrapper Example

Advanced Server SDK Example

Asynchronous Generator Pattern

Extension System

UI Extensions

Dependency Injection Service Extensions