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

Q: How does LlamaIndex ingest vector data from Couchbase (Vector & NoSQL)?

The agent uses vectorsearch to find similar vectors inside Couchbase. LlamaIndex then wraps these results into node objects for immediate retrieval or synthesis.

Q: How do I filter Couchbase (Vector & NoSQL) index schemas in LlamaIndex?

You run listindexes to fetch the active search schemas. LlamaIndex then uses this list to verify which indexes are available before executing a search.

Q: What happens if a Couchbase bucket doesn't exist?

The agent runs listbuckets to check the available routing spaces. If the target bucket isn't there, LlamaIndex handles the error gracefully without crashing your query pipeline.

Index live Couchbase vector searches and NoSQL documents directly into your LlamaIndex RAG pipelines via this MCP Server.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build RAG indexes directly from Couchbase documents

The `get_document` tool pulls raw Couchbase JSON records directly into your LlamaIndex knowledge base using the MCP protocol. LlamaIndex takes these documents, parses their internal mapped properties, and converts them into searchable nodes. Your agent uses `list_scopes` to find the exact collections to index. This ensures your LlamaIndex application only reads from authorized database paths during the ingestion phase.

Query Couchbase (Vector & NoSQL) with LlamaIndex agents

The `vector_search` tool executes KNN vector queries directly on Couchbase indexes to ground your LlamaIndex agent in real-time data. The tool output bypasses standard LLM hallucinations by feeding raw vector matches straight into the query engine. If the agent needs to verify the index status first, it calls `list_indexes` to check active search indexes. This prevents LlamaIndex from querying empty or outdated vector structures.

Run deep text searches across Couchbase clusters

The `fts_search` tool executes full-text search queries against Couchbase asynchronous content trees. LlamaIndex uses this tool to grab relevant text passages when vector search alone isn't enough to answer a complex query. Your agent can also fall back to `execute_n1ql_query` when it needs precise relational filtering on JSON payloads. It gives your LlamaIndex setup a hybrid search system that handles both unstructured text and strict relational data.

Setup guide

Set up Couchbase (Vector & NoSQL) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Couchbase (Vector & NoSQL) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Couchbase (Vector & NoSQL) tools.",
)
response = await agent.run("List recent Couchbase (Vector & NoSQL) data")

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 LlamaIndex

The agent uses `vector_search` to find similar vectors inside Couchbase. LlamaIndex then wraps these results into node objects for immediate retrieval or synthesis.

Yes, you convert the MCP tools using McpToolSpec and pass them to your FunctionAgent. The agent then calls `execute_n1ql_query` or `get_document` based on the user's natural language request.

You run `list_indexes` to fetch the active search schemas. LlamaIndex then uses this list to verify which indexes are available before executing a search.

The agent runs `list_buckets` to check the available routing spaces. If the target bucket isn't there, LlamaIndex handles the error gracefully without crashing your query pipeline.

No, your Couchbase credentials and JSON payloads never leave the secure V8 sandbox. Vinkius acts as an ephemeral proxy, ensuring your raw database records are never logged or stored.

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