How to Use the Couchbase (Vector & NoSQL) MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK handle Couchbase (Vector & NoSQL) vector searches natively?

Yes. The agent uses the vectorsearch tool to execute KNN similarity lookups against your active index. It handles the raw vector comparisons right inside your database, returning clean JSON payloads.

Q: How do guardrails protect Couchbase (Vector & NoSQL) data in OpenAI Agents SDK?

The SDK intercepts calls to tools like executen1qlquery before they hit your database. You write validation logic that checks the generated N1QL parameters, ensuring the agent doesn't execute destructive operations on the MCP Server.

Build production-grade OpenAI Agents SDK systems that query Couchbase (Vector & NoSQL) with built-in safety guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Couchbase (Vector & NoSQL) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Safe Couchbase (Vector & NoSQL) Queries with OpenAI Agents SDK

Your production agents need to pull real data without breaking things. When your agent invokes `execute_n1ql_query` or `get_document`, the SDK validates the action against your defined guardrails before any database execution happens. This keeps your NoSQL data safe while letting the agent find what it needs. You get full tracing on the OpenAI dashboard for every database interaction. If an agent tries to fetch a document from a restricted space, the handoff mechanism routes the task to a specialized agent instead of throwing a generic error.

Fast Vector Search with Auto-Discovered MCP Tools

Skip the manual configuration headache. By passing this MCP Server directly to your agent constructor, the SDK automatically discovers tools like `vector_search` and `fts_search` at runtime. Turn on `cacheToolsList=True` to keep performance tight. Your agent matches KNN vector similarities and runs full-text searches across Couchbase buckets without lagging during live user sessions.

Inspect Database Topography on the Fly

Agents need to know where they are allowed to look. With access to `list_buckets`, `list_scopes`, and `list_indexes`, your agent maps the active Couchbase structure before running complex lookups. This prevents blind query attempts that waste API credits. The agent checks the available scopes and indexes first, choosing the most efficient path to retrieve your target records via the MCP Server.

Setup guide

Set up Couchbase (Vector & NoSQL) MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Couchbase (Vector & NoSQL) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Couchbase (Vector & NoSQL) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Couchbase (Vector & NoSQL) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Couchbase (Vector & NoSQL) Agent",
            instructions="You have access to Couchbase (Vector & NoSQL) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK and use the streamable HTTP server parameter class. Pass the Vinkius endpoint URL into `MCPServerStreamableHttp` within an async context manager, then hand it to your Agent constructor.

Yes. The agent uses the `vector_search` tool to execute KNN similarity lookups against your active index. It handles the raw vector comparisons right inside your database, returning clean JSON payloads.

The SDK intercepts calls to tools like `execute_n1ql_query` before they hit your database. You write validation logic that checks the generated N1QL parameters, ensuring the agent doesn't execute destructive operations on the MCP Server.

The tool returns the raw database error back to the agent. The OpenAI dashboard traces the exact call path, letting you debug whether it was a bad N1QL syntax error or an MCP transport timeout.

All data traffic runs inside an isolated, zero-trust V8 sandbox on Vinkius. Your database credentials and raw JSON payloads never touch external logs, protecting your vectors and NoSQL records from exposure.

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