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

Q: How does Cursor use the Couchbase (Vector & NoSQL) MCP Server to write database queries?

Cursor calls executen1qlquery to run queries against your active Couchbase database. It analyzes the returned Couchbase JSON structure to write precise, typed code that matches your actual schema.

Q: Can Cursor debug my Couchbase (Vector & NoSQL) vector search logic?

Yes, Cursor uses vectorsearch to run Couchbase KNN queries and inspects the index rules returned by listindexes. You see the exact Couchbase similarity scores inside your Cursor editor chat.

Q: How do I verify which Couchbase scopes are available to Cursor?

The listscopes tool retrieves the active Couchbase scopes and collection limits. Cursor runs this automatically when you ask it to inspect your Couchbase database layout.

Inject live Couchbase NoSQL data and KNN vector search results directly into your Cursor editor as you write code.

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 Cursor

Create your Vinkius account to connect Couchbase (Vector & NoSQL) to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate code using real Couchbase MCP Server data

The `get_document` tool pulls real Couchbase KV documents straight into Cursor so your editor writes code against actual data schemas. You stop guessing what your Couchbase JSON payloads look like inside Cursor. Cursor uses these live Couchbase examples to write accurate database access layer code. It eliminates the cycle of running code, seeing a Couchbase schema mismatch, and correcting it manually.

Run Couchbase vector searches inside Cursor

The `vector_search` tool executes Couchbase KNN similarity queries directly from Cursor's agent pane. You test your Couchbase vector search logic without leaving your Cursor workspace. Combined with `fts_search`, you can debug Couchbase text-based content extraction and vector matching inside Cursor. The Cursor editor displays the raw Couchbase search index rules so you know exactly why a query returned a specific document.

Map Couchbase structures on the fly in Cursor

The `list_buckets` tool identifies the routing spaces in your headless Couchbase DB so Cursor understands your architecture. This prevents the Cursor editor from generating queries for non-existent Couchbase collections. Using `list_scopes` and `list_indexes` completes the picture by exposing active Couchbase search rules and collection limits inside Cursor. Cursor builds a temporary mental map of your Couchbase database to keep code generation highly accurate.

Setup guide

Set up Couchbase (Vector & NoSQL) MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Couchbase (Vector & NoSQL) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Couchbase (Vector & NoSQL) transactions." If the MCP tools are loaded correctly, Cursor will call the Couchbase (Vector & NoSQL) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

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

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 Cursor

Cursor calls `execute_n1ql_query` to run queries against your active Couchbase database. It analyzes the returned Couchbase JSON structure to write precise, typed code that matches your actual schema.

Yes, Cursor uses `vector_search` to run Couchbase KNN queries and inspects the index rules returned by `list_indexes`. You see the exact Couchbase similarity scores inside your Cursor editor chat.

No, because this server connects to your remote Couchbase instances securely. Cursor talks to the MCP Server over a secure transport layer, meaning your Couchbase database can live anywhere.

The `list_scopes` tool retrieves the active Couchbase scopes and collection limits. Cursor runs this automatically when you ask it to inspect your Couchbase database layout.

Your Couchbase database credentials and raw JSON payloads are sandboxed within Cursor's secure MCP runtime. Vinkius manages the endpoint token, meaning your Couchbase database keys never sit in plain text in your codebase.

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