How to Use the Vertex AI Vector Search MCP in CrewAI

Q: How does CrewAI orchestrate a vector search using Vertex AI Vector Search?

You assign searchnearestneighbors to an agent's tools. When that agent executes, it receives the endpoint ID and query vector, performing the nearest neighbor similarity check as part of its role-based task.

Q: When should I use Vertex AI Vector Search and CrewAI for monitoring operations?

Use listvectoroperations to give your monitor agent real-time visibility into background indexing jobs. This prevents the entire crew from pausing because a resource is busy building an index.

Q: How do I ensure all my agents know about available vector indexes using Vertex AI Vector Search and CrewAI?

Give your specialized research agent access to listvectorindexes. This ensures that the initial data gathering phase has a complete, up-to-date map of every possible index it can search.

Q: If I need to verify the connection points for my autonomous crew, what tools are best? Vertex AI Vector Search and CrewAI

You'll use listindexendpoints first. This gives you a list of active service endpoints that your agents must connect to before running any search tasks.

Run autonomous multi-agent operations with CrewAI and Vertex AI Vector Search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vertex AI Vector Search MCP to CrewAI

Create your Vinkius account to connect Vertex AI Vector Search 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 Vertex AI Vector Search with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate specialized vector searches between agents.

The `search_nearest_neighbors` tool lets your crew run highly specific vector similarity checks. Agent A can research data, then pass the resulting query vector to Agent B for analysis, making the search results part of a larger, collaborative workflow. This means you're not just running a single query; you're using the output of one agent as input for the next, managing complex information flow across specialized roles.

Monitor and validate index resources.

The `list_vector_operations` tool allows your moderator agent to watch all long-running vector operations. This provides a single source of truth for the entire crew, letting it know if an indexing job is stuck or complete. Additionally, calling `get_index_details` lets a specialized compliance agent check that metadata meets protocol requirements before any action takes place.

Discover all available search targets.

Before the crew can act, it needs to know what's out there. Use `list_vector_indexes` and `list_index_endpoints` to build a definitive map of your project's resources. This ensures that no agent wastes time trying to connect to a non-existent endpoint. If you need to list every potential index, even ones not actively deployed, `list_vector_indexes` is the tool for the job.

Setup guide

Set up Vertex AI Vector Search 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 Vertex AI Vector Search tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Vertex AI Vector Search 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 Vertex AI Vector Search. 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 Vertex AI Vector Search 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 Vertex AI Vector Search MCP in CrewAI

You assign `search_nearest_neighbors` to an agent's tools. When that agent executes, it receives the endpoint ID and query vector, performing the nearest neighbor similarity check as part of its role-based task.

Use `list_vector_operations` to give your monitor agent real-time visibility into background indexing jobs. This prevents the entire crew from pausing because a resource is busy building an index.

Give your specialized research agent access to `list_vector_indexes`. This ensures that the initial data gathering phase has a complete, up-to-date map of every possible index it can search.

This server interacts with Vector Index metadata and deployment status. It manages the structural information around your embeddings, ensuring the system works without exposing raw user query inputs during agent execution.

You'll use `list_index_endpoints` first. This gives you a list of active service endpoints that your agents must connect to before running any search tasks.

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