How to Use the Marqo AI (Vector Search & Embeddings) MCP in Google ADK

Q: How do I add Marqo AI (Vector Search & Embeddings) to a Google ADK agent?

Initialize an McpToolset with StreamableHttpServerParameters pointing to your URL. Pass this toolset directly into the tools array of your LlmAgent.

Q: Can Google ADK filter which Marqo AI (Vector Search & Embeddings) tools are exposed?

Absolutely. You can use the toolnames filter in the ADK to restrict the agent to just tensorsearch and listindexes, preventing accidental document deletions.

Q: Does the agent create indexes automatically?

If you allow it. The createindex tool lets the agent spin up new vector spaces on the fly, which is useful for temporary analytical workflows.

Connect Gemini agents to Marqo AI vector search using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marqo AI (Vector Search & Embeddings) MCP to Google ADK

Create your Vinkius account to connect Marqo AI (Vector Search & Embeddings) to Google ADK 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 Marqo AI (Vector Search & Embeddings) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Massive Context Tensor Search

Gemini models hold over a million tokens in context, but they still need external facts. This MCP Server gives your Google ADK agent the ability to run `tensor_search` against your vector databases. The agent pulls highly relevant semantic matches and dumps them straight into Gemini's massive working memory. Instead of building complex RAG pipelines, you just hand the `McpToolset` to your `LlmAgent`. The agent decides when to search Marqo and when to rely on its own context window.

Direct Document Ingestion via MCP

Enterprise data lives in BigQuery, but semantic search requires vectors. Your agent can read rows from Google Cloud and immediately write them into Marqo using `add_documents`. You define the JSON structure, and the agent handles the ingestion loop. Keeping the index clean is straightforward. When records expire, the agent triggers `delete_documents` by targeting specific IDs. You maintain an accurate vector space without manual intervention.

Index Discovery and Audits

Agents shouldn't guess where your data lives. Before running queries, the agent executes `list_indexes` to see exactly which collections are available. This prevents failed tool calls and wasted compute. You also need to know if an index is ready for production. The `get_index_stats` tool returns configuration details and document counts. The agent can verify the index size before deciding to run a heavy semantic query.

Setup guide

Set up Marqo AI (Vector Search & Embeddings) MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Marqo AI (Vector Search & Embeddings) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Marqo AI (Vector Search & Embeddings)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Marqo AI (Vector Search & Embeddings) tools via MCP.",
    tools=mcp_tools,
)

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 Marqo AI. 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 Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) MCP in Google ADK

Initialize an `McpToolset` with `StreamableHttpServerParameters` pointing to your URL. Pass this toolset directly into the `tools` array of your `LlmAgent`.

Absolutely. You can use the `tool_names` filter in the ADK to restrict the agent to just `tensor_search` and `list_indexes`, preventing accidental document deletions.

The agent runs a tensor query and feeds the resulting JSON chunks into Gemini. Because Gemini handles massive context, you can return hundreds of vector results without truncating the prompt.

If you allow it. The `create_index` tool lets the agent spin up new vector spaces on the fly, which is useful for temporary analytical workflows.

The server handles sensitive JSON catalog records and high-dimensional embeddings. The zero-trust ephemeral architecture guarantees that your enterprise data is only processed in memory for the duration of the tool call, leaving no trace behind.

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