Can my agent perform K-Nearest Neighbor (KNN) vector searches in Couchbase?

Yes. Provide the search index name, the vector embedding array, and the number of results (k). The agent uses Couchbase's native vector capabilities to locate the most semantically similar documents in your cluster.

How do I execute a N1QL query through the agent?

Use the 'execute_n1ql_query' tool and provide your SQL-like statement. The agent will fetch the structural JSON blocks directly from Couchbase, allowing you to perform complex data retrieval using familiar SQL syntax.

Can I search documents using full-text query logic?

Absolutely. The 'fts_search' tool leverages Couchbase's Full-Text Search (FTS) engine. Provide an index name and a boolean query string to perform structural text-based extraction across your document trees.

Couchbase (Vector & NoSQL) MCP Server for Google ADK 7 tools — connect in under 2 minutes

Name: Couchbase (Vector & NoSQL)
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 7 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Couchbase (Vector & NoSQL) as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="couchbase_vector_nosql_agent",
    instruction=(
        "You help users interact with Couchbase (Vector & NoSQL) "
        "using 7 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Couchbase (Vector & NoSQL) MCP Server

Connect your Couchbase (Capella or self-hosted) cluster to any AI agent and take full control of your NoSQL and vector data through natural conversation.

Google ADK natively supports Couchbase (Vector & NoSQL) as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 7 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Vector Search (KNN) — Execute direct searches mapping AI embeddings to locate textual similarities using native vector indices
N1QL SQL-for-JSON — Push absolute explicit querying using N1QL (SQL for Couchbase) to retrieve complex JSON structures across your buckets
Document CRUD — Fetch elaborate internal properties and retrieve exact Data maps from specific collections using unique document keys
Full-Text Search (FTS) — Perform structural text-based extraction matching query strings across advanced FTS search indexes
Schema Navigation — Identify bounded routing spaces including Buckets, Scopes, and Collections to understand your data organization
Index Auditing — Enumerate explicitly registered Search Indexes and verify vector definitions and cluster configurations

The Couchbase (Vector & NoSQL) MCP Server exposes 7 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Couchbase (Vector & NoSQL) to Google ADK via MCP

Follow these steps to integrate the Couchbase (Vector & NoSQL) MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 7 tools from Couchbase (Vector & NoSQL) via MCP

Why Use Google ADK with the Couchbase (Vector & NoSQL) MCP Server

Google ADK provides unique advantages when paired with Couchbase (Vector & NoSQL) through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Couchbase (Vector & NoSQL)

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine Couchbase (Vector & NoSQL) tools with BigQuery, Vertex AI, and Cloud Functions

Couchbase (Vector & NoSQL) + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Couchbase (Vector & NoSQL) MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Couchbase (Vector & NoSQL) and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Couchbase (Vector & NoSQL) tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Couchbase (Vector & NoSQL) regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Couchbase (Vector & NoSQL)

Couchbase (Vector & NoSQL) MCP Tools for Google ADK (7)

These 7 tools become available when you connect Couchbase (Vector & NoSQL) to Google ADK via MCP:

execute_n1ql_query

Provision a highly-available JSON Payload generating generic N1QL constraints

fts_search

Perform structural text-based extraction matching asynchronous Content Trees

get_document

Fetch elaborate internal mapped properties limiting Couchbase KV documents

list_buckets

Identify bounded routing spaces inside the Headless Couchbase DB

list_indexes

Enumerate explicitly attached structured rules exporting active Search Indexes

list_scopes

Retrieve explicit UX logging tracing explicit Scope and Collection Object limits

vector_search

Execute static listing mapping structural KNN Vector similarities via Index

Example Prompts for Couchbase (Vector & NoSQL) in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Couchbase (Vector & NoSQL) immediately.

"List all search indexes in my cluster"

"Find the top 3 similar products using this vector: [0.12, -0.5, 0.88]"

"Run N1QL query: 'SELECT name, price FROM `travel-sample` WHERE price < 100 LIMIT 5'"

Troubleshooting Couchbase (Vector & NoSQL) MCP Server with Google ADK

Common issues when connecting Couchbase (Vector & NoSQL) to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Couchbase (Vector & NoSQL) + Google ADK FAQ

Common questions about integrating Couchbase (Vector & NoSQL) MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.