How to build an AI Agent with Microsoft Agent Framework and the ClickHouse MCP Server

In this guide you'll learn how to build a Microsoft Agent Framework AI agent that can interact with ClickHouse's SQL playground using ClickHouse's MCP Server.

Example notebook

This example can be found as a notebook in the examples repository.

Prerequisites

• You'll need to have Python installed on your system.
• You'll need to have pip installed on your system.
• You'll need an OpenAI API key

You can run the following steps either from your Python REPL or via script.

Install libraries

Install the Microsoft Agent Framework library by running the following commands:

!pip install -q --upgrade pip
!pip install -q agent-framework --pre
!pip install -q ipywidgets

Setup credentials

Next, you'll need to provide your OpenAI API key:

import os, getpass
os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter OpenAI API Key:")

Enter OpenAI API Key: ········

Next, define the credentials needed to connect to the ClickHouse SQL playground:

env = {
    "CLICKHOUSE_HOST": "sql-clickhouse.clickhouse.com",
    "CLICKHOUSE_PORT": "8443",
    "CLICKHOUSE_USER": "demo",
    "CLICKHOUSE_PASSWORD": "",
    "CLICKHOUSE_SECURE": "true"
}

Initialize MCP Server and Microsoft Agent Framework agent

Now configure the ClickHouse MCP Server to point at the ClickHouse SQL playground and also initialize our agent and ask it a question:

from agent_framework import ChatAgent, MCPStdioTool
from agent_framework.openai import OpenAIResponsesClient

clickhouse_mcp_server = MCPStdioTool(
    name="clickhouse",
    command="uv",
    args=[
        "run",
        "--with",
        "mcp-clickhouse",
        "--python",
        "3.10",
        "mcp-clickhouse"
    ],
    env=env
)


async with ChatAgent(
    chat_client=OpenAIResponsesClient(model_id="gpt-5-mini-2025-08-07"),
    name="HousePricesAgent",
    instructions="You are a helpful assistant that can help query a ClickHouse database",
    tools=clickhouse_mcp_server,
) as agent:
    query = "Tell me about UK property prices over the last five years"
    print(f"User: {query}")
    async for chunk in agent.run_stream(query):
        print(chunk.text, end="", flush=True)
    print("\n\n")

The output of running this script is shown below:

User: Tell me about UK property prices over the last five years
I looked at monthly UK sold-price records in the uk.uk_price_paid_simple_partitioned table for the last five years (toStartOfMonth(date), from Oct 2020 → Aug 2025). Summary and key points:

What I measured
- Metrics: monthly median price, mean price, and transaction count (price paid records).
- Period covered: months starting 2020-10-01 through 2025-08-01 (last five years from today).

High-level findings
- Median price rose from £255,000 (2020-10) to £294,500 (2025-08) — an increase of about +15.4% over five years.
  - Equivalent compound annual growth rate (CAGR) for the median ≈ +2.9% per year.
- Mean price fell slightly from about £376,538 (2020-10) to £364,653 (2025-08) — a decline of ≈ −3.2% over five years.
  - Mean-price CAGR ≈ −0.6% per year.
- The divergence (median up, mean slightly down) suggests changes in the mix of transactions (fewer very-high-value sales or other compositional effects), since the mean is sensitive to outliers while the median is not.

Notable patterns and events in the data
- Strong rises in 2020–2021 (visible in both median and mean), consistent with the post‑pandemic / stamp‑duty / demand-driven market surge seen in that period.
- Peaks in mean prices around mid‑2022 (mean values ~£440k), then a general softening through 2022–2023 and stabilisation around 2023–2024.
- Some months show large volatility or unusual counts (e.g., June 2021 and June 2021 had very high transaction counts; March 2025 shows a high median but April–May 2025 show lower counts). Recent months (mid‑2025) have much lower transaction counts in the table — this often indicates incomplete reporting for the most recent months and means recent monthly figures should be treated cautiously.

Example datapoints (from the query)
- 2020-10: median £255,000, mean £376,538, transactions 89,125
- 2022-08: mean peak ~£441,209 (median ~£295,000)
- 2025-03: median ~£314,750 (one of the highest medians)
- 2025-08: median £294,500, mean £364,653, transactions 18,815 (low count — likely incomplete)

Caveats
- These are transaction prices (Price Paid dataset) — actual house “values” may differ.
- Mean is sensitive to composition and outliers. Changes in the types of properties sold (e.g., mix of flats vs detached houses, regional mix) will affect mean and median differently.
- Recent months can be incomplete; months with unusually low transaction counts should be treated with caution.
- This is a national aggregate — regional differences can be substantial.

If you want I can:
- Produce a chart of median and mean over time.
- Compare year-on-year or compute CAGR for a different start/end month.
- Break the analysis down by region/county/town, property type (flat, terraced, semi, detached), or by price bands.
- Show a table of top/bottom regions for price growth over the last 5 years.

Which follow-up would you like?