Statespace
Enables users to document data and connect it to AI agents by defining tools and instructions in markdown files. It supports building RAG and text-to-SQL applications that can be deployed as MCP servers, APIs, or CLIs.
README
<br>
<div align="center"> <picture> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/statespace-tech/statespace/main/docs/assets/images/header_light.png" /> <img src="https://raw.githubusercontent.com/statespace-tech/statespace/main/docs/assets/images/header_dark.png" alt="Statespace" width="375" /> </picture> </div>
<div align="center">
<br>
Self-documenting AI applications
</div>
Website: https://statespace.com
Documentation: https://docs.statespace.com
AI doesn't know your data. Statespace helps you build self-documenting data applications that describe themselves to agents. Build RAG, text-to-SQL, and knowledge bases that agents can maintain and improve over time. Once you’ve created an app, you can deploy, manage, and share it from our cloud platform.
Quickstart
Get up and running with your first app by asking your coding agent:
claude "Create a Statespace app: https://statespace.com/AGENTS.md"
Example
1. Create it
Create a new PostgreSQL app with:
statespace init --text-to-sql postgresql://user:pass@host:port/db
This creates an app skeleton with just enough tools and instructions for your agent to explore your database:
---
tools:
- [psql, -d, $DB, -c, { regex: "^SELECT\\b.*" }]
---
# Instructions
- Learn the schema by exploring tables, columns, and relationships
- Translate the user's question into a query that answers it
2. Build it
Build your full app by iterating on it with your coding agent:
claude "Document my database's schema and add a script to summarize them"
Your agent will spin up a local server to test your app:
statespace serve .demo/ --port 8000
The result is a self-documenting app that any agent can understand and use:
demo/
├── README.md # from above
├── script.py
└── schema/
├── users.md
└── products.md
3. Ship it
Optionally, create a free Statespace account to deploy your app and get a shareable URL:
statespace deploy path/to/app/
Then, connect any agent to your app through our API or MCP.
<details open> <summary>API</summary>
Pass the public URL to your agent:
claude "Use the API at https://demo.statespace.app to find out the number of users"
</details>
<details> <summary>MCP</summary>
Configure the MCP client:
"statespace": {
"command": "uvx",
"args": ["statespace-mcp", "https://demo.statespace.app"]
}
</details>
Example skeletons
Community & Contributing
- Discord: Join our community server for real-time help and discussions
- X: Follow us @statespace_tech for updates and news
- Issues: Report bugs or request features on GitHub Issues
License
This project is licensed under the terms of the MIT license.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.