Skip to main content

ByteHouse MCP Server

An MCP server for ByteHouse. ByteHouse MCP Server serves as a communication bridge between large language models and ByteHouse instances, capable of efficiently transmitting information to achieve seamless docking and collaboration between the two. It also provides intelligent services throughout the entire life cycle for ByteHouse data development, query optimization, and cluster operation and maintenance. During data development, it offers precise guidance and suggestions to improve efficiency and quality. In terms of query optimization, it supports the analysis of statements and the optimization of performance. In the aspect of cluster operation and maintenance, it provides services such as monitoring the status, warning of risks, and automatic diagnosis and repair to ensure the efficient operation of the system.

Features

Tools

  • run_select_query

    • Execute SQL queries on your ByteHouse cluster.
    • Input: sql (string): The SQL query to execute.
    • All ByteHouse queries are run with readonly = 1 to ensure they are safe.
  • list_databases

    • List all databases on your ByteHouse cluster.
  • list_tables

    • List all tables in a database.
    • Input: database (string): The name of the database.
  • run_dml_ddl_query

    • Execute DML or DDL queries on your ByteHouse cluster.
    • Input: sql (string): The SQL query to execute.

Configuration

Running the Server

# Run the server with stdio transport (default)
mcp-bytehouse

# Run the server with SSE transport
mcp-bytehouse --transport sse
  1. Open the Claude Desktop configuration file located at:

    • On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • On Windows: %APPDATA%/Claude/claude_desktop_config.json
  2. Add the following:

{
  "mcpServers": {
    "mcp-bytehouse": {
      "command": "uvx",
      "args": [
            "--from",
            "git+https://github.com/volcengine/mcp-server@main#subdirectory=server/mcp_server_bytehouse",
            "mcp_bytehouse",
      ],
      "env": {
        "BYTEHOUSE_HOST": "<ByteHouse-host>",
        "BYTEHOUSE_PORT": "<ByteHouse-port>",
        "BYTEHOUSE_USER": "<ByteHouse-user>",
        "BYTEHOUSE_PASSWORD": "<ByteHouse-password>",
        "BYTEHOUSE_SECURE": "true",
        "BYTEHOUSE_VERIFY": "true",
        "BYTEHOUSE_CONNECT_TIMEOUT": "30",
        "BYTEHOUSE_SEND_RECEIVE_TIMEOUT": "30"
      }
    }
  }
}

License

This project is licensed under the Apache License.

Release files for mcp-bytehouse 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mcp-bytehouse 0.2.0
File Size Uploaded
mcp_bytehouse-0.2.0.tar.gz 81.6 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for mcp-bytehouse 0.2.0
File Interpreter ABI Platform
mcp_bytehouse-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 92.9 kB

Release files / mcp_bytehouse-0.2.0.tar.gz

Download URL mcp_bytehouse-0.2.0.tar.gz
Size 81.6 kB
Tags Source
SHA-256 checksum
How to use checksums
a12d568ead29b63d8e2bb0565d42fa2dfccb93b688c68b2fd56df7321015d1d2
BLAKE2b-256 checksum
How to use checksums
af677285062fab300603d5c27e85286d8e880a60fd5874f4f01d10ddcf2b902d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.14

Release files / mcp_bytehouse-0.2.0-py3-none-any.whl

Download URL mcp_bytehouse-0.2.0-py3-none-any.whl
Size 11.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
62cb6a4adadb518f53e178d9e52b9a589a229fc0a9f4094feaf1c4832f476c17
BLAKE2b-256 checksum
How to use checksums
07eb47dda9b1e515f73305301bdb68b314f507bf8cc5305cba94b5dbb6e3dbc3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.14

Release history Release notifications | RSS feed

This release

0.2.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page