How to Use the Redis Vector MCP in CrewAI

Q: Can I restrict which CrewAI agents can access the Redis Vector MCP Server?

Yes. Use MCPServerHTTP with a toolfilter to only expose searchvectors to your reader agents, while limiting structural changes to your admin agent.

Q: How does CrewAI share Redis Vector search results between agents?

CrewAI uses shared memory. When one agent runs searchvectors, the resulting document keys and similarity scores are placed in the crew's context, allowing subsequent agents to read them.

Deploy specialized agent teams that collaborate to index, search, and clean up Redis Vector databases in CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Redis Vector MCP to CrewAI

Create your Vinkius account to connect Redis Vector to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Redis Vector with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative Vector Database Operations

Divide your database tasks among specialized agents. In CrewAI, you can have a Research Agent generate raw text, an Embeddings Agent call `upsert_vector` to store the floats, and a QC Agent run `search_vectors` to confirm the write. This multi-agent MCP setup prevents a single model from getting overwhelmed. Each agent focuses on one aspect of your Redis index, passing state through shared memory.

CrewAI MCP Server Integration

Let your crew keep your database tidy. A moderator agent can run `list_indexes` and `get_index_info` to check the health and size of your RediSearch schemas. If the moderator agent spots dead indexes or bloated vector spaces, it instructs a worker agent to run `delete_vector` on stale keys, keeping your memory usage optimized.

Hierarchical Search and Retrieval

Implement multi-stage retrieval pipelines. Your lead CrewAI agent manages the search by calling `search_vectors` to pull relevant document IDs from Redis. It then hands those IDs to subordinate agents to compile reports, draft emails, or update external systems, running the entire operation without human oversight.

Setup guide

Set up Redis 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 Redis Vector tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Redis 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 Redis Vector. 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 Redis 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 Redis Vector MCP in CrewAI

You can pass your Vinkius URL directly in the agent's mcps list. CrewAI automatically connects to the endpoint and exposes the entire suite of vector tools to that specific agent.

Yes. Use MCPServerHTTP with a tool_filter to only expose `search_vectors` to your reader agents, while limiting structural changes to your admin agent.

CrewAI uses shared memory. When one agent runs `search_vectors`, the resulting document keys and similarity scores are placed in the crew's context, allowing subsequent agents to read them.

CrewAI connects via HTTP or SSE to the managed Vinkius endpoint, letting your python-based crew communicate with the Redis tools over a secure, persistent connection.

Vinkius executes every tool call inside an isolated, ephemeral V8 sandbox. Your database credentials, keys, and float arrays are processed entirely in memory and wiped the instant the execution completes.

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