How to Use the DataStax Astra DB Vector MCP in CrewAI

Q: How can I make a CrewAI agent that only searches DataStax Astra DB Vector?

When defining your agent in CrewAI, use the toolfilter option in the MCPServerHTTP configuration. You can specify that this agent should only have access to tools like vectorsearch and finddocuments.

Q: Can different agents in my CrewAI crew share data from Astra DB?

Yes. One agent can perform a vectorsearch, place the resulting document IDs into the shared context, and another agent can then use those IDs with findonedocument to retrieve the full records.

Deploy autonomous agent crews that manage and search your DataStax Astra DB Vector data with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DataStax Astra DB Vector MCP to CrewAI

Create your Vinkius account to connect DataStax Astra DB Vector 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 DataStax Astra DB Vector with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign Database Tasks to Your Crew

With CrewAI, you can create specialized agents for database operations. Assign a 'Researcher' agent the `vector_search` and `find_documents` tools to gather information from Astra DB. This agent's only job is to query the database efficiently. Then, a separate 'Analyst' agent can take those findings and process them. You can even have a 'Janitor' agent whose role is to use `delete_document` for cleanup tasks, ensuring a clean separation of concerns within your crew.

Coordinate Database Ops with Your MCP Server

Build crews that work together on your data. An 'Ingestion' agent could use `insert_document` to add new articles to a collection. A 'Verifier' agent could then follow up, using `find_one_document` to check that the data was written correctly and is properly vectorized. This multi-agent approach is perfect for building autonomous ETL or data quality pipelines. The shared memory in CrewAI lets agents pass document IDs or search results between each other, coordinating complex sequences of tasks against your MCP Server.

Monitor Astra DB with an Agent Crew

Set up a 'Monitor' agent that periodically runs `count_documents` on a critical collection. If the count drops unexpectedly, it can delegate a task to an 'Investigator' agent. The 'Investigator' agent can then use `find_documents` with specific filters to figure out what happened. This lets you build self-healing, autonomous systems that watch over your Astra DB data via this MCP without any human needing to be involved.

Setup guide

Set up DataStax Astra DB Vector 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 DataStax Astra DB Vector tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent DataStax Astra DB Vector 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="DataStax Astra DB Vector Analyst",
        goal="Access and analyze DataStax Astra DB Vector data via MCP.",
        backstory="Expert analyst with direct DataStax Astra DB Vector access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent DataStax Astra DB Vector 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 DataStax Astra DB. 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 DataStax Astra DB Vector 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 DataStax Astra DB Vector MCP in CrewAI

When defining your agent in CrewAI, use the `tool_filter` option in the `MCPServerHTTP` configuration. You can specify that this agent should only have access to tools like `vector_search` and `find_documents`.

Yes. One agent can perform a `vector_search`, place the resulting document IDs into the shared context, and another agent can then use those IDs with `find_one_document` to retrieve the full records.

Absolutely. You can have one agent identify old or irrelevant documents using `find_documents` and another agent, with the `delete_document` tool, execute the deletion. This creates a safe and autonomous maintenance process.

For a quick start, just pass your Vinkius URL directly into the `mcps` list when creating your Agent. CrewAI will automatically fetch and register all the available tools from the server.

Each tool call from your CrewAI agent is handled in a separate, stateless Vinkius execution environment. Your document and collection data is processed in memory for the duration of the call and then wiped. Authentication is managed by your Vinkius token, so your Astra DB keys are never 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