How to Use the Couchbase (Vector & NoSQL) MCP in VS Code Copilot

Q: How do we configure the Couchbase (Vector & NoSQL) MCP Server for our entire team in VS Code Copilot?

You commit a .vscode/mcp.json file containing the Couchbase server configuration to your repository. Every developer using VS Code Copilot gets instant access to the Couchbase database tools.

Q: Can VS Code Copilot run vector similarity searches on Couchbase (Vector & NoSQL)?

Yes, VS Code Copilot uses the vectorsearch tool to execute KNN queries. It maps the Couchbase vector similarities and presents the closest matching records inside your editor.

Q: How does VS Code Copilot retrieve specific documents from Couchbase (Vector & NoSQL)?

VS Code Copilot calls the getdocument tool to fetch Couchbase KV documents. It limits the retrieved properties to avoid cluttering your VS Code workspace with massive Couchbase JSON payloads.

Q: What tools does VS Code Copilot use to discover our Couchbase indexes?

The MCP Server uses listindexes to enumerate your active Couchbase search indexes. VS Code Copilot reads these rules to understand how your vector and text searches are structured.

Equip your engineering team with live Couchbase vector search and NoSQL queries directly inside VS Code Copilot.

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 VS Code Copilot

Create your Vinkius account to connect Couchbase (Vector & NoSQL) to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Share Couchbase MCP Server access across your team

The `execute_n1ql_query` tool runs structured Couchbase queries directly from VS Code Copilot using a shared team configuration. Every developer on your team queries Couchbase without managing individual database credentials. VS Code Copilot uses these Couchbase query results to explain database performance and debug query constraints in real-time. It brings consistency to how your team interacts with the Couchbase database layer inside VS Code.

Test Couchbase vector and text searches in Copilot

The `vector_search` tool runs Couchbase KNN vector queries directly inside the VS Code Copilot chat window. Your developers verify Couchbase search results without jumping into a database console. For text-based queries, `fts_search` extracts asynchronous Couchbase content trees to test search indexes inside VS Code Copilot. Copilot analyzes these Couchbase results to help you fine-tune your search relevance.

Inspect Couchbase documents inside VS Code Copilot

The `get_document` tool pulls specific Couchbase KV documents directly into your VS Code Copilot editor context. VS Code Copilot limits the properties it fetches to keep the chat responsive. To understand the database layout, `list_scopes`, `list_buckets`, and `list_indexes` map out your active Couchbase search rules and collection boundaries. This gives VS Code Copilot the Couchbase structure it needs to write flawless queries.

Setup guide

Set up Couchbase (Vector & NoSQL) MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Couchbase (Vector & NoSQL) MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Couchbase (Vector & NoSQL) tools listed. Try asking: "List my recent Couchbase (Vector & NoSQL) transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

You commit a `.vscode/mcp.json` file containing the Couchbase server configuration to your repository. Every developer using VS Code Copilot gets instant access to the Couchbase database tools.

Yes, VS Code Copilot uses the `vector_search` tool to execute KNN queries. It maps the Couchbase vector similarities and presents the closest matching records inside your editor.

VS Code Copilot calls the `get_document` tool to fetch Couchbase KV documents. It limits the retrieved properties to avoid cluttering your VS Code workspace with massive Couchbase JSON payloads.

The MCP Server uses `list_indexes` to enumerate your active Couchbase search indexes. VS Code Copilot reads these rules to understand how your vector and text searches are structured.

All Couchbase database queries and JSON payloads run through an isolated V8 sandbox on Vinkius. Your Couchbase credentials stay encrypted, and no raw data is ever stored on the Vinkius platform.

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