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

Q: How do I connect CrewAI to the ClickHouse (Vector Search) MCP Server?

Pass your Vinkius HTTP endpoint directly into the mcps array when defining your agent. For more granular control, import MCPServerHTTP from crewai.mcp and use a tool filter to restrict which agents can execute arbitrary SQL.

Deploy autonomous AI teams in CrewAI to monitor ClickHouse health, map schemas, and run vector searches without human intervention.

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 CrewAI

Create your Vinkius account to connect ClickHouse (Vector Search) to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate database ops with this MCP Server

A researcher agent uses `list_databases` and `list_tables` to map the environment, while a separate analyst agent constructs the actual queries. Giving a single script full database access through the MCP is risky, and CrewAI lets you split responsibilities across specialized roles. When the researcher runs `describe_table`, the exact column schemas stay in context. Teams share memory across the entire execution session. The analyst agent uses that shared knowledge to run arbitrary SQL without needing to ask the database for structural hints again.

Monitor cluster limits autonomously

You can assign a monitor agent to repeatedly call `get_table_stats` on a schedule. High-availability setups need constant observation. It watches row counts and memory usage, triggering a moderator agent if the cluster health degrades during heavy ingestion. The monitor runs `get_version` to verify HNSW support before passing control to the search agent. Version constraints dictate what your agents can do. This hierarchical execution ensures no agent attempts an unsupported operation on the active runtime.

Execute massive embedding searches

Your search agent receives user intent, formats the mathematical arrays, and calls `vector_search`. Finding nearest neighbors across millions of rows takes precise execution. It filters the exact distance traces and hands the results back to a summarizer agent. Combining embedding proximity with `execute_sql` lets the crew perform deep analytical joins autonomously. Raw SQL execution handles the complex aggregations that standard vector matching misses, delivering finished reports instead of raw data dumps.

Setup guide

Set up ClickHouse (Vector Search) MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke ClickHouse (Vector Search) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="ClickHouse (Vector Search) Analyst",
    goal="Access and analyze ClickHouse (Vector Search) data via MCP.",
    backstory="Expert analyst with direct ClickHouse (Vector Search) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent ClickHouse (Vector Search) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="ClickHouse (Vector Search) Analyst",
        goal="Access and analyze ClickHouse (Vector Search) data via MCP.",
        backstory="Expert analyst with direct ClickHouse (Vector Search) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent ClickHouse (Vector Search) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass your Vinkius HTTP endpoint directly into the `mcps` array when defining your agent. For more granular control, import `MCPServerHTTP` from `crewai.mcp` and use a tool filter to restrict which agents can execute arbitrary SQL.

Splitting access is highly recommended. You should give your read-only agents access to the discovery tools, while reserving the execution tools strictly for your specialized database administrator agent.

The framework maintains shared memory across the entire crew. When an agent extracts table statistics or schema definitions, that context becomes immediately available to the rest of the team for subsequent tasks.

Your agents manage failures based on their configured delegation rules when interacting with the MCP. If a massive aggregation drops, the executing agent can ask a peer for help or adjust the query structure before trying again.

Nobody outside your active session. The Vinkius zero-trust environment processes your vector payloads and analytical statements in a temporary sandbox, destroying the entire execution state the moment your Python script finishes running.

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