Does this work with Couchbase Capella?

Yes, this MCP connects to both Capella and self-hosted Couchbase clusters.

Which AI clients can I use with this MCP?

You can use any MCP-compatible client, including Claude, Cursor, and Windsurf.

Can I perform vector searches?

Yes, the MCP includes a capability for executing KNN vector similarity searches via your existing indices.

Can I run standard SQL queries?

You can run N1QL queries, which is the SQL-for-JSON language used by Couchbase.

Do I need to manage the connection myself?

No, Vinkius hosts and manages the MCP, so you only need to connect your client once.

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' capability 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' capability 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.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Couchbase Vector Nosql to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Query and manage your Couchbase clusters through natural language.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 7 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through Couchbase.

01
Execute n1ql query
Runs N1QL queries to pull specific JSON payloads using SQL-like constraints.
02
List buckets
Identifies the available buckets within your Couchbase database.
03
List indexes
Shows all active search indexes currently attached to your data.
04
List scopes
Retrieves the specific scopes and collection limits for your data organization.

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Couchbase.

05
Fts search
Performs text-based searches across your content trees using full-text search indexes.
06
Get document
Fetches specific KV documents and their internal properties using unique keys.
07
Vector search
Executes KNN vector similarity searches using your existing vector indices.

Real work

What teams actually run

RAG Debugging

Test how well your vector embeddings match your actual Couchbase data.

Data Auditing

Verify that your JSON documents follow the expected schema across different collections.

Rapid Prototyping

Build search features quickly by asking your agent to find specific data patterns.

Index Management

Check the status and definitions of your search and vector indexes.

Automate a task

Put Couchbase to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Couchbase works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Couchbase to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

914ms average. Fast in production.

Couchbase is checked daily against the live service.

Daily averagePeak 1141ms

Oct 3Today

Fastest day: 753ms
Slowest day: 1141ms
14-day trend: Stable+4%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Couchbase, so you can see the experience inside your AI.

It does not authenticate your account with Couchbase. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Couchbase Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_wWaJnEVjNwe96vxf5IajtX1h1rZH9VkCF8KWnsvT/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Couchbase capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "couchbase-vector-nosql-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_wWaJnEVjNwe96vxf5IajtX1h1rZH9VkCF8KWnsvT/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Couchbase in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Couchbase owners hand off.

This MCP is built for technical users who need to bridge the gap between unstructured NoSQL data and AI-driven workflows.

01
AI Developers
They use the MCP to debug vector similarity and semantic matching for RAG.
02
Data Architects
They use it to audit NoSQL structures and verify how collections are organized.
03
Database Administrators
They use it to monitor search indexes and run N1QL queries to check data consistency.

FAQ

Questions Couchbase owners ask.

01
Does this work with Couchbase Capella?
Yes, this MCP connects to both Capella and self-hosted Couchbase clusters.
02
Which AI clients can I use with this MCP?
You can use any MCP-compatible client, including Claude, Cursor, and Windsurf.
03
Can I perform vector searches?
Yes, the MCP includes a capability for executing KNN vector similarity searches via your existing indices.
04
Can I run standard SQL queries?
You can run N1QL queries, which is the SQL-for-JSON language used by Couchbase.
05
Do I need to manage the connection myself?
No, Vinkius hosts and manages the MCP, so you only need to connect your client once.
06
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.
07
How do I execute a N1QL query through the agent?
Use the 'execute_n1ql_query' capability 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.
08
Can I search documents using full-text query logic?
Absolutely. The 'fts_search' capability 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.

Explore

More in Databases

Connect Couchbase to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Execute n1ql query

List buckets

List indexes

List scopes

05-07

Fts search

Get document

Vector search

What teams actually run

RAG Debugging

Data Auditing

Rapid Prototyping

Index Management

Building your own app? The connector is yours to use.

Couchbase Connector

Claude Desktop

AI Developers

Data Architects

Database Administrators

Does this work with Couchbase Capella?

Which AI clients can I use with this MCP?

Can I perform vector searches?

Can I run standard SQL queries?

Do I need to manage the connection myself?

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

How do I execute a N1QL query through the agent?

Can I search documents using full-text query logic?

ClickHouse (Vector Search) AI Connector

Elasticsearch Vector AI Connector

Marqo AI (Vector Search & Embeddings) AI Connector

MongoDB Atlas Vector Search AI Connector

Suggestions

Redis Vector AI Connector

Typesense Vector Search AI Connector

Vertex AI Vector Search AI Connector

Lucidworks Fusion (AI Search & Discovery) AI Connector