A powerful MCP server connection providing real-time SQL access to over 50 premium datasets directly within your AI coding agent or IDE.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install baselight-mcp
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install baselight-mcp using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Baselight MCP skill enables AI agents to interact with a vast repository of structured data from over 50 premium sources including Kaggle, World Bank, SEC filings, and real-time financial markets. By bridging the gap between LLMs and live databases, this skill allows developers to perform complex data analysis and retrieval tasks without leaving their IDE.
Using Openclaw Skills like Baselight MCP ensures that your AI coding environment has access to verifiable, high-fidelity data rather than relying solely on model training data. It supports standard SQL syntax for querying tables, making it an essential tool for data science, financial analysis, and research-heavy development workflows.
To integrate this into your workflow, configure your MCP client using the server URL. For OAuth-based clients like ChatGPT or Claude Desktop, use the standard connection flow. For CLI or IDE tools like VS Code or Gemini CLI, generate an API key from the Baselight dashboard.
# MCP Server URL
https://api.baselight.app/mcp
Ensure you have an active Baselight account to manage authentication and monitor query usage limits.
Baselight organizes data using a hierarchical namespace for easy discovery and cross-source querying. Tables are referenced using a specific syntax to avoid naming collisions.
| Level | Format | Description |
|---|---|---|
| Namespace | @username | Represents the data provider or specific user account. |
| Dataset | .dataset | A logical collection of related tables (e.g., soccer, finance). |
| Table | .table | The specific structured data entity to be queried. |
Example Reference: @user.soccer.matches
Loading
A powerful batch processing system for executing large-scale AI inference requests asynchronously with significant cost savings.

A high-performance batch processing skill for running asynchronous AI inference jobs at scale through the Doubleword API.

A high-performance MLX-based skill for generating images locally on Apple Silicon using FLUX.2 and Z-Image models.

A competitive arena where AI agents battle in a virtual computer using the classic CoreWar programming game.

A command-line tool designed to search the coches.net marketplace and retrieve comprehensive listing details in table or JSON formats.

A command-line interface designed to search and retrieve detailed property listing data from the Idealista marketplace.








































