How to Use the ClickHouse (Vector Search) MCP in AutoGen

Q: How do I register ClickHouse (Vector Search) MCP Server tools with AutoGen agents?

Use the mcpservertools helper with your Vinkius HTTP transport parameters. Pass the resulting tool list directly into your AssistantAgent constructor.

Q: Can AutoGen agents debate the results of a ClickHouse (Vector Search) MCP Server query?

Yes, one agent can execute vectorsearch and share the output with the group. Other agents can then analyze the distances and debate whether the matches are relevant.

Q: How do AutoGen agents handle SQL errors from the ClickHouse (Vector Search) MCP Server?

When executesql returns an error, the executing agent shares the traceback in the conversation. A coding agent can then rewrite the SQL and try again.

Let your AutoGen agents debate and execute complex ClickHouse vector queries in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ClickHouse (Vector Search) MCP to AutoGen

Create your Vinkius account to connect ClickHouse (Vector Search) 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 ClickHouse (Vector Search) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run ClickHouse MCP Server queries via agent debate

The `vector_search` tool executes mathematical distance traces across your database. AutoGen agents can collaborate to solve complex data retrieval problems. One agent can draft a vector query, while another uses this tool to execute it and verify the results. They discuss the outputs until they reach a consensus on the best answer. To ensure they are querying the right dataset, the agents use `list_databases` and `list_tables` to verify the active schemas. This collaborative approach prevents run-time errors and bad queries.

Safe SQL execution through agent verification

The `execute_sql` tool runs arbitrary DML or DDL commands inside your agent workflow. Running write operations can be risky, but AutoGen lets a developer agent write a query and a supervisor agent execute it only after verifying the syntax. This double-check mechanism keeps your database safe from destructive commands. Before running any heavy queries, the agents inspect the table structure using `describe_table`. This ensures the schema matches the query design before execution.

Monitor cluster performance dynamically

The `get_table_stats` tool checks internal structural states to track cluster health. High-speed searches require a healthy database, and your monitoring agent can periodically call this tool to check the status. If performance degrades, the agent can notify the team or adjust query parameters. The agent also uses `get_version` to verify engine capabilities, such as HNSW index support. This ensures your system only attempts advanced vector searches when the database is fully capable of handling them.

Setup guide

Set up ClickHouse (Vector Search) 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 ClickHouse (Vector Search) 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="ClickHouse (Vector Search)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent ClickHouse (Vector Search) 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="ClickHouse (Vector Search)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent ClickHouse (Vector Search) 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 ClickHouse. 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 ClickHouse (Vector Search) 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 ClickHouse (Vector Search) MCP in AutoGen

Use the `mcp_server_tools` helper with your Vinkius HTTP transport parameters. Pass the resulting tool list directly into your `AssistantAgent` constructor.

Yes, one agent can execute `vector_search` and share the output with the group. Other agents can then analyze the distances and debate whether the matches are relevant.

When `execute_sql` returns an error, the executing agent shares the traceback in the conversation. A coding agent can then rewrite the SQL and try again.

No, the MCP tool adapter handles all schema conversions automatically. The tools are exposed to your agents with correct JSON schemas.

Vinkius handles all database authentication at the proxy level. The MCP Server handles all database authentication, so your agents only interact with the standardized tool interfaces, keeping your raw credentials completely hidden.

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