BlazeSQL MCP Server

Integrations

  • Handles API key authentication securely via environment variables for connecting to the BlazeSQL service.

  • Provides integration with BlazeSQL Natural Language Query API, allowing users to query databases using natural language requests and receive SQL queries and formatted results.

  • Used to implement the MCP server that connects to BlazeSQL's API, enabling natural language database querying capabilities.

BlazeSQL MCP Server

This project implements a Model Context Protocol (MCP) server that acts as a proxy to the BlazeSQL Natural Language Query API. It allows MCP-compatible clients (like Cursor, Claude 3 with tool use, the MCP Inspector, etc.) to interact with BlazeSQL using natural language.

Features

  • Exposes the BlazeSQL Natural Language Query API as an MCP tool named blazesql_query.
  • Handles API key authentication securely via environment variables.
  • Communicates with clients using the standard MCP stdio transport.

Workflow Diagram

This diagram shows the sequence of interactions when a client uses the blazesql_query tool:

Prerequisites

Setup

  1. Clone the Repository:
    git clone <repository-url> cd blaze-sql-mcp-server
  2. Install Dependencies:
    yarn install
  3. Configure Environment Variables:
    • Copy the example environment file:
      cp .env.sample .env
    • Edit the .env file:
      # .env BLAZE_API_KEY=YOUR_BLAZESQL_API_KEY_HERE
      Replace YOUR_BLAZESQL_API_KEY_HERE with your actual API key obtained from your BlazeSQL account settings.

Running the Server

  1. Build the Server: Compile the TypeScript code to JavaScript:
    yarn build
  2. Run the Server: Execute the compiled code:
    node build/index.js
    The server will start and log messages to stderr (you might see "API Key loaded successfully..." etc.). It is now listening for an MCP client connection via standard input/output (stdio).

Connecting an MCP Client

This server uses the stdio transport mechanism.

  1. Make sure the server is not already running separately.
  2. Run the Inspector, telling it to launch your server:
    npx @modelcontextprotocol/inspector node build/index.js
  3. The Inspector UI will launch, automatically connecting to your server.
  4. Navigate to the "Tools" tab to interact with the blazesql_query tool.

Using Integrated Clients (Cursor, Claude 3, etc.)

  1. Start the server in a terminal:
    node build/index.js
  2. Configure the client: In your MCP client's settings, you need to add a custom server configuration.
    • Transport: Select stdio.
    • Command: Specify the exact command used to run the server. You need to provide the absolute path to node and the absolute path to the build/index.js file.
      • Example (macOS/Linux - adjust paths as needed): /usr/local/bin/node /Users/your_username/path/to/blaze-sql-mcp-server/build/index.js
      • You can find the path to node using which node in your terminal.
      • You can find the path to the project using pwd inside the project directory.
    • Save the configuration.
  3. The client should now be able to connect to your locally running server and list/use its tools.

Using the blazesql_query Tool

Once connected, the client can call the blazesql_query tool.

  • Tool Name: blazesql_query
  • Arguments:
    • db_id (string, required): The ID of the target database connection in your BlazeSQL account. You can find this ID in the BlazeSQL web application when managing your database connections.
    • natural_language_request (string, required): The query you want to execute, written in plain English (e.g., "show me the total number of users").
  • Example Call (using mcp test syntax for illustration):
    call-tool blazesql_query --db_id "db_your_actual_db_id" --natural_language_request "What were the total sales last month?"
  • Output: If successful, the tool returns:
    • A text block containing the natural language response from the BlazeSQL agent.
    • A code block (language sql) containing the SQL query generated and executed by BlazeSQL.
    • A json block containing the actual data results from the query. If unsuccessful, it returns an MCP error message.

You must be authenticated.

A
security – no known vulnerabilities
F
license - not found
A
quality - confirmed to work

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

A Model Context Protocol server that enables AI clients to interact with BlazeSQL's Natural Language Query API, allowing natural language queries against SQL databases.

  1. Features
    1. Workflow Diagram
      1. Prerequisites
        1. Setup
          1. Running the Server
            1. Connecting an MCP Client
              1. Using the MCP Inspector (Recommended for Testing)
              2. Using Integrated Clients (Cursor, Claude 3, etc.)
            2. Using the blazesql_query Tool

              Related MCP Servers

              • -
                security
                A
                license
                -
                quality
                A Model Context Protocol server enabling AI agents to access and manipulate ServiceNow data through natural language interactions, allowing users to search for records, update them, and manage scripts.
                Last updated -
                9
                Python
                MIT License
              • -
                security
                A
                license
                -
                quality
                A Model Context Protocol server that enables natural language queries to MySQL databases, powered by XiYanSQL text-to-SQL technology.
                Last updated -
                94
                Python
                Apache 2.0
                • Linux
                • Apple
              • -
                security
                A
                license
                -
                quality
                A Model Context Protocol server that enables AI agents to query Erick Wendel's talks, blog posts, and videos across different platforms using natural language.
                Last updated -
                55
                TypeScript
                MIT License
              • -
                security
                F
                license
                -
                quality
                A Model Context Protocol server that enables AI models to interact with MySQL databases through natural language, supporting SQL queries, table creation, and schema exploration.
                Last updated -
                1
                Python
                • Linux
                • Apple

              View all related MCP servers

              ID: y6icx0ab46