How to Use the Couchbase (Vector & NoSQL) MCP in Google ADK

Q: How do I configure the Couchbase (Vector & NoSQL) MCP Server toolset in Google ADK?

Use the McpToolset class with your Vinkius HTTP transport parameters. Pass this toolset directly into your LlmAgent initialization to expose the database tools to Gemini.

Q: How does Gemini leverage Couchbase (Vector & NoSQL) vector search?

The agent calls the vectorsearch tool to execute KNN queries against your Couchbase search indexes. Gemini then processes the returned vector matches inside its long-context window.

Connect Couchbase (Vector & NoSQL) to Google ADK to run deep reasoning over massive vector databases.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Couchbase (Vector & NoSQL) MCP to Google ADK

Create your Vinkius account to connect Couchbase (Vector & NoSQL) 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 Couchbase (Vector & NoSQL) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Gemini Reasoning Over Couchbase (Vector & NoSQL) MCP Server

Feed your Couchbase records directly into Gemini's million-token context window. By exposing tools like `get_document` and `execute_n1ql_query` to your Google ADK agent, you bridge the gap between your live NoSQL database and enterprise reasoning models. The agent reads complex JSON payloads and cross-references them with your existing Google Cloud data. It handles raw database outputs without requiring you to write custom parser code.

Bridge BigQuery Data with Live NoSQL State

Your enterprise data lives in multiple places. Use this MCP Server to let your agent fetch active Couchbase states with `get_document` and compare them against historical analytical tables in BigQuery. This setup gives your agent a complete view of your systems. It pulls the operational Couchbase data, joins it with analytical insights, and executes next steps instantly.

Map Indexes and Scopes in Enterprise Projects

Large enterprise deployments have strict boundaries. The agent uses `list_scopes`, `list_buckets`, and `list_indexes` to discover exactly where it is allowed to search within your Couchbase cluster. You can restrict the toolset to expose only specific operations. This ensures the Gemini agent only queries the collections and search indexes relevant to its current task using the MCP standard.

Setup guide

Set up Couchbase (Vector & NoSQL) 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 Couchbase (Vector & NoSQL) 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="Couchbase (Vector & NoSQL)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Couchbase (Vector & NoSQL) 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 Couchbase. 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 Couchbase (Vector & NoSQL) 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 Couchbase (Vector & NoSQL) MCP in Google ADK

Use the `McpToolset` class with your Vinkius HTTP transport parameters. Pass this toolset directly into your `LlmAgent` initialization to expose the database tools to Gemini.

Yes. You can pass a filtered list of tool names to the toolset configuration. This prevents the agent from seeing tools like `execute_n1ql_query` if you only want it running `vector_search`.

The agent calls the `vector_search` tool to execute KNN queries against your Couchbase search indexes. Gemini then processes the returned vector matches inside its long-context window.

Yes. The Vinkius deployment handles the HTTP connection, which Google ADK consumes using standard streamable parameters. You don't have to manage local binaries or node processes for this MCP Server.

Yes. Vinkius executes the database connector inside an ephemeral sandbox. Your raw JSON documents, scopes, and vector indexes are accessed via encrypted HTTPS tunnels, ensuring no data leaks into the public LLM training sets.

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