OPENAPI Spec For Clickhouse Cloud

Provides a configurable MCP server that exposes an OpenAPI-based interface for multi-agent conversations with support for multiple transport modes.

python

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "huazhengwang-openapi-spec-for-clickhouse-cloud": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "A JSON string containing the configuration.",
        "SECURITY": "Environment variables for security parameters (e.g., API keys).",
        "CONFIG_PATH": "Path to a JSON configuration file (e.g., mcp_server/mcp_config.json) or leave unset to load from another source."
      }
    }
  }
}

This MCP Server provides a dedicated bridge to the given OpenAPI URL, enabling you to run the server locally and connect clients via the Multi-Agent Conversation Protocol. It supports flexible transport modes and is designed to work with Python environments, making it straightforward to run, test, and integrate into your tooling.

How to use

You run the MCP server locally and connect your MCP clients to it using the built-in stdio transport. Start the server with the recommended Python command, then initiate a client connection via the MCP protocol. The server reads its configuration from environment variables or a JSON configuration file, allowing you to tailor security and startup behavior. Use the server to query the OpenAPI backend, exchange messages with agents, and orchestrate multi-agent conversations through the MCP protocol.

How to install

Prerequisites: you need Python 3.9 or newer, plus pip and the uv runtime.

Step 1. Prepare your environment and install dependencies.

Step 2. Clone the repository.

Step 3. Install development dependencies.

Step 4. Run the server using the stdio transport.

Server configuration and startup

You can configure the server through environment variables. The supported variables are CONFIG_PATH for a JSON configuration file path, CONFIG for an inline JSON configuration, and SECURITY for security-related settings such as API keys.

To start the server in stdio mode, use the following command.

Configuration references

Environment variables to configure the server include:

CONFIG_PATH — Path to a JSON configuration file (e.g., mcp_server/mcp_config.json)
CONFIG — A JSON string containing the configuration
SECURITY — Environment variables for security parameters (e.g., API keys)

Notes on tooling and testing

Development and testing rely on standard Python tooling. Linting and type checking use Ruff and Mypy, while tests run with Pytest. You can run the tests, static analysis, and lint checks as part of your local workflow.

Built by

VeilStrat

AI signals for GTM teams