How to Use the Amazon Bedrock KB MCP in CrewAI

Q: How can one CrewAI agent find documents in Amazon Bedrock KB for another agent to use?

Assign the retrieve tool to a 'Researcher' agent. It will query the Bedrock KB and get source documents. It can then pass this context to another agent in the crew for analysis or summarization.

Q: Can a CrewAI team monitor the sync status of an Amazon Bedrock KB?

Yes. An agent can be tasked to periodically call the listingestionjobs tool. It can then analyze the output to check for failures and pass the results to another agent for reporting or alerting.

Q: What's the easiest way to get started with Amazon Bedrock KB and CrewAI?

Just pass your Vinkius MCP Server URL into the mcps parameter when defining your Agent in CrewAI. The agent will automatically discover and be able to use all the Bedrock KB tools.

Q: How do I limit which Bedrock KB tools a specific CrewAI agent can use?

When you set up the MCPServerHTTP object in CrewAI, use the toolfilter argument. This lets you provide a list of tool names, like 'retrieve', 'retrieveandgenerate', restricting the agent to only those actions.

Equip your CrewAI agent teams with direct access to query and manage any Amazon Bedrock KB.

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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialize Your CrewAI Agents

Assign specific roles to your agents. One agent, the 'Researcher,' can use the `retrieve` tool to find all relevant documents in your Amazon Bedrock KB. It passes those documents to a second 'Writer' agent. The 'Writer' agent's only job is to synthesize the information provided by the Researcher. This separation of concerns, a core CrewAI concept, ensures answers are strictly based on the retrieved context. This MCP Server provides the tools to make that division of labor possible.

Build a Crew to Manage Your KBs

You can deploy a CrewAI team to keep your knowledge bases healthy. An 'Auditor' agent could run daily, using `list_knowledge_bases` and `list_data_sources` to check for configuration drift. If the Auditor finds a problem, it passes the details to another agent. That agent can then track the fix by watching the output of `list_ingestion_jobs`. It's a simple way to build an autonomous monitoring system with this MCP Server.

Grounded Answers for CrewAI

The `retrieve_and_generate` tool is a simple way to give any agent in your crew the ability to answer questions using your private data. It's a single tool call that performs a vector search on your Bedrock KB and generates a fact-based response. By adding this MCP Server to your CrewAI agents' toolset, you ensure their outputs are grounded in reality. Whether you're building a research team or a customer support crew, their conclusions will come from your documents, not the LLM's general knowledge.

Setup guide

Set up Amazon Bedrock KB MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Amazon Bedrock KB tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Amazon Bedrock KB Analyst",
    goal="Access and analyze Amazon Bedrock KB data via MCP.",
    backstory="Expert analyst with direct Amazon Bedrock KB access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Amazon Bedrock KB transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Amazon Bedrock KB Analyst",
        goal="Access and analyze Amazon Bedrock KB data via MCP.",
        backstory="Expert analyst with direct Amazon Bedrock KB access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Amazon Bedrock KB transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Assign the `retrieve` tool to a 'Researcher' agent. It will query the Bedrock KB and get source documents. It can then pass this context to another agent in the crew for analysis or summarization.

Yes. An agent can be tasked to periodically call the `list_ingestion_jobs` tool. It can then analyze the output to check for failures and pass the results to another agent for reporting or alerting.

Just pass your Vinkius MCP Server URL into the `mcps` parameter when defining your Agent in CrewAI. The agent will automatically discover and be able to use all the Bedrock KB tools.

When you set up the `MCPServerHTTP` object in CrewAI, use the `tool_filter` argument. This lets you provide a list of tool names, like `['retrieve', 'retrieve_and_generate']`, restricting the agent to only those actions.

Your query strings and any data pulled from your Bedrock KB are processed within a secure, single-use Vinkius environment. The connection is ephemeral; no data is logged or stored after your agent's task is complete. Your AWS credentials are managed by the server and are not exposed.

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