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

Q: How do AutoGen agents coordinate Couchbase (Vector & NoSQL) writes?

While this MCP server focuses on reads, agents can use executen1qlquery to run data manipulation queries. The agents debate the query structure before the execution agent runs it.

Q: Can one AutoGen agent pass Couchbase (Vector & NoSQL) results to another?

Yes, when an agent calls getdocument, the raw JSON payload becomes part of the shared conversation history. The other agents can then read and analyze that data in the next turn.

Q: How do AutoGen agents discover Couchbase (Vector & NoSQL) buckets?

The agents call listbuckets to identify the available routing spaces in your database. This lets them dynamically target the correct bucket during their cooperative task execution.

Let your AutoGen agents debate and execute Couchbase vector searches and N1QL queries in real-time using 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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents audit Couchbase document schemas

The `get_document` tool fetches raw JSON documents from Couchbase through this MCP connection so your AutoGen agents can inspect their internal structures. One agent can retrieve the document while another debates whether the schema matches your application's requirements. The agents use `list_scopes` to trace the boundaries of your collections. This keeps the multi-agent conversation grounded in actual database paths instead of guessed configurations.

Run Couchbase (Vector & NoSQL) searches via AutoGen debate

The `vector_search` tool runs KNN search queries on Couchbase vector indexes, letting your AutoGen agents retrieve semantic matches. A retrieval agent can fetch the vectors while a critic agent analyzes if the results meet the similarity threshold. If the similarity score is too low, the agents can coordinate to run `list_indexes` and switch to a different index. This consensus-driven search ensures your agents don't settle for bad data.

Execute complex N1QL queries through agent consensus

The `execute_n1ql_query` tool runs structured queries against your Couchbase database using N1QL constraints. Your AutoGen execution agent runs the query, while a security agent checks the query structure for injection risks before it fires. The agents can also run `fts_search` to pull unstructured text matches when SQL-like queries aren't enough. Having both tools available lets the agent group decide the best retrieval strategy for the task.

Setup guide

Set up Couchbase (Vector & NoSQL) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Couchbase (Vector & NoSQL) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Couchbase (Vector & NoSQL)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Couchbase (Vector & NoSQL) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Couchbase (Vector & NoSQL)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Couchbase (Vector & NoSQL) data")
    print(result.messages[-1].content)

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 AutoGen

While this MCP server focuses on reads, agents can use `execute_n1ql_query` to run data manipulation queries. The agents debate the query structure before the execution agent runs it.

Yes, when an agent calls `get_document`, the raw JSON payload becomes part of the shared conversation history. The other agents can then read and analyze that data in the next turn.

The agents call `list_buckets` to identify the available routing spaces in your database. This lets them dynamically target the correct bucket during their cooperative task execution.

Yes, the McpToolAdapter converts the Couchbase tool schemas into the format AutoGen expects. This allows your agents to understand the tool parameters without manual mapping.

Vinkius executes the server in a zero-trust, ephemeral V8 sandbox. Your database credentials and retrieved JSON records are processed in-memory and are never stored on disk or exposed to external networks.

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