databasesai-ml

ToolFront▌

by kruskal-labs

ToolFront is a knowledge database software and db management system offering unified access to databases with advanced t

Provides unified access to multiple database types including PostgreSQL, MySQL, SQLite, DuckDB, BigQuery, and Snowflake with tools for schema inspection, data sampling, read-only querying, and intelligent pattern matching across tables.

github stars

★ 824

GitHub npm

Supports 6 major database typesRead-only access for safe explorationUnified interface across different databases

best for

/ Data analysts working with multiple database systems
/ Developers building database-agnostic applications
/ Data exploration and discovery workflows
/ Cross-database reporting and analysis

capabilities

/ Query PostgreSQL, MySQL, SQLite, DuckDB, BigQuery, and Snowflake databases
/ Inspect database schemas and table structures
/ Sample data from tables for exploration
/ Perform read-only queries across different database types
/ Match patterns and search across table data
/ Browse database contents without modification

what it does

Provides unified access to multiple database types (PostgreSQL, MySQL, SQLite, DuckDB, BigQuery, Snowflake) with schema inspection, data sampling, and querying capabilities.

about

ToolFront is a community-built MCP server published by kruskal-labs that provides AI assistants with tools and capabilities via the Model Context Protocol. ToolFront is a knowledge database software and db management system offering unified access to databases with advanced t It is categorized under databases, ai ml.

how to install

You can install ToolFront in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.

license

MIT

ToolFront is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.

readme

# Statespace **Build interactive web apps for AI agents in Markdown.** [![Test Suite](https://github.com/statespace-tech/statespace/actions/workflows/test.yml/badge.svg)](https://github.com/statespace-tech/statespace/actions/workflows/test.yml) [![License](https://img.shields.io/badge/license-MIT-007ec6?style=flat-square)](https://github.com/statespace-tech/statespace/blob/main/LICENSE) [![Discord](https://img.shields.io/discord/1323415085011701870?label=Discord&logo=discord&logoColor=white&color=5865F2&style=flat-square)](https://discord.gg/rRyM7zkZTf) [![X](https://img.shields.io/badge/Statespace-black?style=flat-square&logo=x&logoColor=white)](https://x.com/statespace_tech)

--- **Website: [https://statespace.com](https://statespace.com/)** **Documentation: [https://docs.statespace.com](https://docs.statespace.com/)** --- _A declarative framework for building AI-friendly web applications that agents can navigate and interact with._ ## Installation Install the CLI: ```bash curl -fsSL https://statespace.com/install.sh | bash ``` ## Example ### Create it Start with one file: `README.md` ````yaml --- tools: - [expr] --- ```component echo "Random number: $RANDOM" ``` # Instructions - The component loads a random number when the page loads - Use the `expr` tool to perform calculations with it ```` ### Serve it Save the example above as `myapp/README.md` and run: ```bash $ statespace serve myapp/ Running on `http://127.0.0.1:8000` ``` ### Ask it Pass the URL to any agent that can make HTTP requests: ```bash claude "Multiply the random number in http://127.0.0.1:8000 by 256" ``` ### Deploy it Create a free [Statespace account](https://statespace.com/auth/login) and deploy your app to the cloud: ```bash $ statespace deploy myapp/ Deployed to https://myapp.statespace.app ``` ## Concepts

Tools — Give agents controlled access to CLI commands over HTTP.

```yaml --- tools: - [grep] - [curl, -X, GET, { }] - [psql, -c, { regex: "^SELECT\b.*" }] --- ```

Components — Render live data inside component code blocks.

````yaml ```component echo "Server time: $(date)" ``` ````

Instructions — Guide agents through your data, workflows, and pages.

```markdown # Instructions - Use grep to search for logs in ./data - Query the database for recent users - See [analyze](src/analyze.md) for more workflows ```

## Features ✅ **Simple** — It's just Markdown. Easy to learn, easy to use, easy to maintain. ⚡ **Lightweight** — Install a single Rust binary. No dependencies. 🌐 **Universal** — Works immediately with any agent that can make HTTP requests. 📦 **Portable** — Deploy apps to the cloud for a public URL, or run them locally. 🔒 **Secure** — Restrict access to your private apps with token-based authentication. ## Community & Contributing - **Discord**: Join our [community server](https://discord.gg/rRyM7zkZTf) for real-time help and discussions - **X**: Follow us [@statespace_tech](https://x.com/statespace_tech) for updates and news - **Issues**: Report bugs or request features on [GitHub Issues](https://github.com/statespace-tech/statespace/issues) ## License This project is licensed under the terms of the MIT license.