How to Use the Amazon Bedrock KB MCP in LangChain

Q: How do I pass Amazon Bedrock KB tool outputs into a LangChain prompt template?

Map the output of retrieve directly to your prompt's context variable. The tool returns raw text chunks that you feed into your template before sending the payload to your LLM.

Q: What is the setup process for this integration?

Install langchain-mcp-adapters and initialize the MCP client with the Vinkius HTTP endpoint. Grab the tools with client.gettools() and pass them directly to your agent constructor.

Run multi-step AWS retrieval chains with LangChain and Amazon Bedrock KB to ground your agents in live enterprise data.

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 LangChain

Create your Vinkius account to connect Amazon Bedrock KB to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground LangChain agents using the Amazon Bedrock KB MCP Server

This MCP server exposes `retrieve` and `retrieve_and_generate` to feed verified AWS knowledge base results directly into your LangChain runnables. Your agent queries the vector index, receives grounded context, and formulates answers without hallucinating. You track the entire retrieval path inside LangSmith. The tool outputs flow as raw text nodes into your prompt templates, letting you inspect latency and vector distance metrics for every single query.

Control Bedrock ingestion directly from your chains

The `list_ingestion_jobs` and `list_data_sources` tools give your LangChain agent direct visibility into your AWS data pipeline status. If a user asks why their latest document is missing, the agent checks the sync status on the fly. You build self-healing chains that trigger alerts or pause queries when an ingestion job fails. This keeps your agent from making decisions based on stale vector indices.

Inspect AWS Bedrock structures dynamically

The `get_knowledge_base` and `list_knowledge_bases` tools let your LangChain agent discover which vector targets are active. Instead of hardcoding IDs, the agent queries AWS to find the right index for the user's specific department. This dynamic routing saves you from writing complex branching logic in python. The agent inspects the available metadata and selects the correct knowledge base ID automatically.

Setup guide

Set up Amazon Bedrock KB MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Amazon Bedrock KB tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "amazon-bedrock-kb-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Amazon Bedrock KB transactions"
    })
    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 LangChain

Map the output of `retrieve` directly to your prompt's context variable. The tool returns raw text chunks that you feed into your template before sending the payload to your LLM.

Yes, every tool execution shows up as a distinct step in your LangSmith trace. You see the exact query sent to `retrieve` and the raw vector chunks returned from AWS.

The LangChain MCP adapter wraps the connection in standard execution blocks. If the server drops, your chain throws a standard python exception that you catch with standard error-handling runnables.

Install `langchain-mcp-adapters` and initialize the MCP client with the Vinkius HTTP endpoint. Grab the tools with `client.get_tools()` and pass them directly to your agent constructor.

Vinkius runs the server in a sandboxed V8 isolate, meaning your AWS keys and vector query inputs never persist. Only the raw query strings pass through the runtime to hit the AWS Bedrock endpoint, leaving no local footprint.

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