Cómo crear un agente de IA con LangChain/LangGraph usando el servidor MCP de ClickHouse.

En esta guía, aprenderás a crear un agente de IA con LangChain/LangGraph que pueda interactuar con el SQL playground de ClickHouse mediante el servidor MCP de ClickHouse.

Notebook de ejemploPuedes encontrar este ejemplo como un notebook en el repositorio de ejemplos.

Requisitos previos

Debes tener Python instalado en tu sistema.
Debes tener pip instalado en tu sistema.
Necesitarás una clave de API de Anthropic o una clave de API de otro proveedor de LLM.

Puedes ejecutar los siguientes pasos desde tu REPL de Python o mediante un script.

Instalar bibliotecas

Instale las bibliotecas requeridas ejecutando los siguientes comandos:

pip install -q --upgrade pip
pip install -q langchain-mcp-adapters langgraph "langchain[anthropic]"

Configura las credenciales

A continuación, tendrás que proporcionar tu clave de API de Anthropic:

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

Response

Enter Anthropic API Key: ········

Uso de otro proveedor de LLMSi no tienes una clave de API de Anthropic y quieres usar otro proveedor de LLM, puedes consultar las instrucciones para configurar tus credenciales en la documentación de proveedores de LangChain

Inicialice el servidor MCP

Ahora configure el ClickHouse MCP server para que apunte al ClickHouse SQL playground:

from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client

server_params = StdioServerParameters(
    command="uv",
    args=[
        "run",
        "--with", "mcp-clickhouse",
        "--python", "3.13",
        "mcp-clickhouse"
    ],
    env={
        "CLICKHOUSE_HOST": "sql-clickhouse.clickhouse.com",
        "CLICKHOUSE_PORT": "8443",
        "CLICKHOUSE_USER": "demo",
        "CLICKHOUSE_PASSWORD": "",
        "CLICKHOUSE_SECURE": "true"
    }
)

Configura el manejador del flujo

Al trabajar con Langchain y ClickHouse MCP server, los resultados de las consultas suelen devolverse como datos en streaming en lugar de una única respuesta. En el caso de grandes conjuntos de datos o consultas analíticas complejas cuyo procesamiento puede llevar tiempo, es importante configurar un manejador del flujo. Sin un manejo adecuado, esta salida en streaming puede ser difícil de utilizar en tu aplicación.Configura el manejador para la salida en streaming de modo que sea más fácil de procesar:

class UltraCleanStreamHandler:
    def __init__(self):
        self.buffer = ""
        self.in_text_generation = False
        self.last_was_tool = False
        
    def handle_chunk(self, chunk):
        event = chunk.get("event", "")
        
        if event == "on_chat_model_stream":
            data = chunk.get("data", {})
            chunk_data = data.get("chunk", {})
            
            # Only handle actual text content, skip tool invocation streams
            if hasattr(chunk_data, 'content'):
                content = chunk_data.content
                if isinstance(content, str) and not content.startswith('{"'):
                    # Add space after tool completion if needed
                    if self.last_was_tool:
                        print(" ", end="", flush=True)
                        self.last_was_tool = False
                    print(content, end="", flush=True)
                    self.in_text_generation = True
                elif isinstance(content, list):
                    for item in content:
                        if (isinstance(item, dict) and 
                            item.get('type') == 'text' and 
                            'partial_json' not in str(item)):
                            text = item.get('text', '')
                            if text and not text.startswith('{"'):
                                # Add space after tool completion if needed
                                if self.last_was_tool:
                                    print(" ", end="", flush=True)
                                    self.last_was_tool = False
                                print(text, end="", flush=True)
                                self.in_text_generation = True
                                
        elif event == "on_tool_start":
            if self.in_text_generation:
                print(f"\n🔧 {chunk.get('name', 'tool')}", end="", flush=True)
                self.in_text_generation = False
                
        elif event == "on_tool_end":
            print(" ✅", end="", flush=True)
            self.last_was_tool = True

Llama al agente

Por último, llama a tu agente y pregúntale quién ha aportado más código a ClickHouse:

async with stdio_client(server_params) as (read, write):
    async with ClientSession(read, write) as session:
        await session.initialize()
        tools = await load_mcp_tools(session)
        agent = create_react_agent("anthropic:claude-sonnet-4-0", tools)
        
        handler = UltraCleanStreamHandler()        
        async for chunk in agent.astream_events(
            {"messages": [{"role": "user", "content": "Who's committed the most code to ClickHouse?"}]}, 
            version="v1"
        ):
            handler.handle_chunk(chunk)
            
        print("\n")

Deberías ver una respuesta similar a la que se muestra a continuación:

Response

I'll help you find who has committed the most code to ClickHouse by exploring the available databases and tables to locate git commit data.
🔧 list_databases ✅ I can see there's a `git` database which likely contains git commit information. Let me explore the tables in that database:
🔧 list_tables ✅ Perfect! I can see the `clickhouse_commits` table in the git database contains ClickHouse commit data with 80,644 commits. This table has information about each commit including the author, lines added/deleted, files modified, etc. Let me query this table to find who has committed the most code based on different metrics.
🔧 run_select_query ✅ Let me also look at just the lines added to see who has contributed the most new code:
🔧 run_select_query ✅ Based on the ClickHouse git commit data, **Alexey Milovidov** has committed the most code to ClickHouse by several measures:

## Key Statistics:

1. **Most Total Lines Changed**: Alexey Milovidov with **1,696,929 total lines changed** (853,049 added + 843,880 deleted)
2. **Most Lines Added**: Alexey Milovidov with **853,049 lines added**
3. **Most Commits**: Alexey Milovidov with **15,375 commits**
4. **Most Files Changed**: Alexey Milovidov with **73,529 files changed**

## Top Contributors by Lines Added:

1. **Alexey Milovidov**: 853,049 lines added (15,375 commits)
2. **s-kat**: 541,609 lines added (50 commits) 
3. **Nikolai Kochetov**: 219,020 lines added (4,218 commits)
4. **alesapin**: 193,566 lines added (4,783 commits)
5. **Vitaly Baranov**: 168,807 lines added (1,152 commits)

Alexey Milovidov is clearly the most prolific contributor to ClickHouse, which makes sense as he is one of the original creators and lead developers of the project. His contribution dwarfs others both in terms of total code volume and number of commits, with nearly 16,000 commits and over 850,000 lines of code added to the project.

​Requisitos previos

Requisitos previos