How to Use the Amazon Bedrock KB MCP in LlamaIndex

Q: How do I convert Amazon Bedrock KB tool outputs into LlamaIndex Document nodes?

Call retrieve to get the raw text chunks, then wrap them in standard LlamaIndex Document objects. You can then insert these nodes directly into your local vector store index.

Q: Can I use LlamaIndex query engines to search Amazon Bedrock KB?

Yes, by wrapping the retrieve tool in an McpToolSpec and passing it to your agent. The agent queries the AWS vector store and uses the results to answer user prompts.

Q: How do I configure tool filtering for the Amazon Bedrock KB MCP Server inside LlamaIndex?

Use the allowedtools filter when initializing your McpToolSpec. This lets you restrict your agent to only the retrieve tool, preventing it from calling ingestion tools.

Q: How do I initialize this server in my python script?

Install llama-index-tools-mcp and instantiate the MCP client with your Vinkius endpoint. Convert it using McpToolSpec and call totoollistasync to get the tools.

Index live AWS vector data into your LlamaIndex RAG applications 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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live vector queries into LlamaIndex

This MCP server provides the `retrieve` tool to pull raw vector matches from AWS Bedrock directly into your LlamaIndex document store. You convert these live search results into node objects for immediate local indexing. Your query engines then search both local documents and these freshly pulled AWS nodes. This merges your cloud-hosted enterprise knowledge with local, session-specific context.

Ground LlamaIndex query engines with managed RAG

The `retrieve_and_generate` tool lets your LlamaIndex agent offload the entire retrieval-augmented generation loop to AWS Bedrock. Instead of building local chunking and synthesis pipelines, you let Bedrock handle the generation and return the final answer. This reduces local CPU overhead and keeps your token usage predictable. You get a fully synthesized response backed by AWS security protocols in a single tool call.

Monitor AWS data sources from your index pipelines

The `list_data_sources` and `list_ingestion_jobs` tools expose the current sync state of your AWS data pipelines to your LlamaIndex workflows. Your pipeline checks if a sync is active before running expensive index evaluations. If a sync is running, your query engine waits or warns the user that the vector index is currently updating. This prevents index mismatch errors during automated tests.

Setup guide

Set up Amazon Bedrock KB MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Amazon Bedrock KB MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Amazon Bedrock KB tools.",
)
response = await agent.run("List recent Amazon Bedrock KB data")

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 LlamaIndex

Call `retrieve` to get the raw text chunks, then wrap them in standard LlamaIndex `Document` objects. You can then insert these nodes directly into your local vector store index.

Yes, by wrapping the `retrieve` tool in an `McpToolSpec` and passing it to your agent. The agent queries the AWS vector store and uses the results to answer user prompts.

Use the `allowed_tools` filter when initializing your `McpToolSpec`. This lets you restrict your agent to only the `retrieve` tool, preventing it from calling ingestion tools.

Install `llama-index-tools-mcp` and instantiate the MCP client with your Vinkius endpoint. Convert it using `McpToolSpec` and call `to_tool_list_async` to get the tools.

Your AWS access keys and query payloads are processed entirely in memory within an ephemeral V8 sandbox. No vector data, AWS metadata, or ingestion logs are stored on Vinkius disks.

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