How to Use the Amazon Bedrock KB MCP in Pydantic AI

Build type-safe agents with Pydantic AI and Amazon Bedrock KB for reliable, validated RAG.

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 Pydantic AI

Create your Vinkius account to connect Amazon Bedrock KB to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce schema in Pydantic AI

Every response from `retrieve` is validated against your Pydantic models. If the knowledge base returns malformed data, your agent catches it instantly. This prevents silent errors from propagating through your system. You get a clean, typed interface for all your document retrieval tasks.

Query indexes with Pydantic AI

You can use `list_knowledge_bases` to discover available indices and verify their status before running queries. This metadata is parsed into your models for easy access. It makes your agent code more readable and easier to maintain. You aren't guessing what the API returns.

Ground responses in Pydantic AI

Implement `retrieve_and_generate` to get structured answers from your knowledge base. The output is validated automatically, ensuring your agent only works with data that matches your requirements. It removes the risk of hallucinated fields in your output. Your agent stays strictly within the boundaries you set.

Setup guide

Set up Amazon Bedrock KB MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "amazon-bedrock-kb-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Amazon Bedrock KB tools.",
)

result = await agent.run("List recent Amazon Bedrock KB transactions")
print(result.output)

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 Pydantic AI

The MCP server sends raw JSON which your Pydantic models then parse. If the structure doesn't match your definition, the agent raises a validation error immediately.

You can register multiple toolsets in your agent configuration. Each one can connect to a different knowledge base, giving your agent access to diverse data.

Yes, just ensure your server is running in a stable environment. The type-safe nature of this setup makes it ideal for critical production tasks.

Because you are using Pydantic, you can log the validation errors. This tells you exactly which field failed and why the data didn't match your schema.

The server performs strict schema validation on all inputs and outputs. This prevents injection attacks and ensures that only sanitized, expected data types reach your Pydantic-defined agent logic.

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