Skip to main content
Skip to main content
Edit this page

Using ClickHouse MCP server with Ollama

This guide explains how to use the ClickHouse MCP Server with Ollama.

Install Ollama​

Ollama is a library for running Large Language Models (LLMs) on your own machine. It has a wide range of models available and is easy to use.

You can download Ollama for Mac, Windows, or Linux from the download page.

Once you run Ollama, it will start a local server in the background that you can use to run models. Alternatively, you can run the server manually by running ollama serve.

Once installed, you can pull a model down to your machine like this:

This will pull the model to your local machine if it is not present. Once it's downloaded, you can run the model like this:

Note

Only models that have tool support will work with MCP Servers.

We can list the models that we have downloaded like this:

We can use the following command to see more information about the model that we've downloaded:

We can see from this output that the default qwen3 model has just over 8 billion parameters.

Install MCPHost​

At the time of writing (July 2025) there is no native functionality for using Ollama with MCP Servers. However, we can use MCPHost to run Ollama models with MCP Servers.

MCPHost is a Go application, so you'll need to make sure that you have Go installed on your machine. You can then install MCPHost by running the following command:

The binary will be installed under ~/go/bin so we need to make sure that directory is on our path.

Configuring ClickHouse MCP Server​

We can configure MCP Servers with MCPHost in YAML or JSON files. MCPHost will look for config files in your home directory the following order:

  1. .mcphost.yml or .mcphost.json (preferred)
  2. .mcp.yml or .mcp.json (backwards compatibility)

It uses a syntax that's similar to that used in the standard MCP configuration file. Here's an example of a ClickHouse MCP server configuration, which we'll save to the ~/.mcphost.json file:

The main difference from the standard MCP configuration file is that we need to specify a type. The type is used to indicate the transport type used by the MCP Server.

  • local → stdio transport
  • remote → streamable transport
  • builtin → inprocess transport

We'll also need to configure the following environment variables:

Note

In theory, you should be able to provide these variables under the environment key in the MCP configuration file, but we've found that this doesn't work.

Running MCPHost​

Once you've configured the ClickHouse MCP server, you can run MCPHost by running the following command:

Or, if you want to have it use a specific config file:

Caution

If you don't provide --model, MCPHost will look in the environment variables for ANTHROPIC_API_KEY and will use the anthropic:claude-sonnet-4-20250514 model.

We should see the following output:

We can use the /servers command to list the MCP Servers:

And /tools to list the tools available:

We can then ask the model questions about the databases/tables available in the ClickHouse SQL playground.

In our experience when using smaller models (the default qwen3 model has 8 billion parameters), you'll need to be more specific about what you'd like it to do. For example, you'll need to explicitly ask it to list the databases and tables rather than straight away asking it to query a certain table. You can partially eleviate this problem by using a large model (e.g. qwen3:14b), but that will run more slowly on consumer hardware.