How to Use the Amazon Bedrock KB MCP in AutoGen

Q: How do I register Amazon Bedrock KB tools with an AutoGen agent?

Use the mcpservertools helper with your Vinkius server URL to fetch the tools. Pass the resulting list directly into your AssistantAgent constructor.

Let your AutoGen agents debate and verify AWS data using the Amazon Bedrock KB MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon Bedrock KB MCP to AutoGen

Create your Vinkius account to connect Amazon Bedrock KB to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Amazon Bedrock KB with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Verify AWS Bedrock data through AutoGen agent debate

This MCP server exposes `retrieve` and `get_knowledge_base` to your AutoGen agent group, allowing multiple agents to cross-examine retrieved vector data. One agent pulls the context, while a critic agent analyzes the text for hallucination before approving the final response. This multi-agent verification prevents bad vector matches from polluting your conversation history. You get highly accurate answers because the agents debate the validity of the AWS results.

Coordinate AWS Bedrock syncs using AutoGen agents

The `list_ingestion_jobs` and `list_data_sources` tools allow your supervisor agent to track data pipeline status while worker agents prepare new files. The supervisor agent blocks document queries if an active ingestion job is still running on AWS. This automated coordination prevents agents from reading incomplete vector spaces. The conversation stays paused until the sync tool reports a successful run.

Use Amazon Bedrock KB for secure multi-agent generation

The `retrieve_and_generate` tool provides your AutoGen assistant agent with a direct path to Bedrock's managed RAG engine. Instead of writing custom prompt loops for every agent in the group, the assistant delegates the generation step to AWS. The resulting text is then passed back to the group chat for further analysis or formatting. This keeps your agent logic clean and leverages AWS's optimized generation models.

Setup guide

Set up Amazon Bedrock KB MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Amazon Bedrock KB tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Amazon Bedrock KB_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Amazon Bedrock KB data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Amazon Bedrock KB_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Amazon Bedrock KB data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Amazon Bedrock. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Amazon Bedrock KB now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Amazon Bedrock KB MCP in AutoGen

Use the `mcp_server_tools` helper with your Vinkius server URL to fetch the tools. Pass the resulting list directly into your `AssistantAgent` constructor.

Yes, you register the tools with the group chat manager or assign specific tools like `retrieve` to a dedicated research agent. The agents then call the tools as needed during their conversation.

The MCP tool adapter automatically translates the server schemas into the format AutoGen expects. You do not need to write custom JSON schemas or manual conversion code.

The server supports both stdio and Streamable HTTP transports. When hosted on Vinkius, you connect via the Streamable HTTP endpoint using your secure token.

Your AWS credentials and vector queries are isolated in a zero-trust, ephemeral V8 container. The server processes the requests in memory and discards all session data immediately after the tool call completes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript