Statespace
Enables AI agents to interact with DuckDB for high-performance analytical queries.
Provides connectivity for AI agents to access and work with MongoDB databases.
Allows AI agents to explore schemas and execute queries on MySQL databases.
Connects AI agents to PostgreSQL databases for data documentation, schema exploration, and text-to-SQL tasks.
Enables the execution of Python scripts as custom tools within AI agent workflows.
Facilitates interaction with Snowflake data warehouses, allowing AI agents to perform queries and analyze data.
Supports AI-driven data exploration and querying of local SQLite databases.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@StatespaceHow many new users registered this week?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
statespace
Search documentation indexed from llms.txt sites — from the terminal, from your AI assistant, or over HTTP.
CLI
npx statespace search "redis connection pooling"
npx statespace search "authentication" --site upstash.com
npx statespace search "rate limiting" --limit 20Options
Flag | Short | Default | Description |
|
| — | Restrict to a specific site (name, domain, or URL) |
|
| 10 | Max results |
|
|
| Backend API base URL |
MCP
Add to your MCP client config (Claude Desktop, Cursor, etc.):
{
"mcpServers": {
"statespace": {
"command": "npx",
"args": ["statespace", "mcp"]
}
}
}For a remote backend:
{
"mcpServers": {
"statespace": {
"command": "npx",
"args": ["statespace", "mcp", "--url", "https://your-backend.example.com"]
}
}
}To run as an SSE server instead of stdio (useful for remote or multi-client deployments):
npx statespace mcp --transport sse --port 4000Tool: search
Parameter | Type | Required | Default | Description |
| string | yes | — | Search query |
| integer | no | 10 | Max results |
| string | no | — | Restrict to a specific site (name, domain, or URL) |
HTTP
The backend exposes a single endpoint:
GET /search?q=<query>[&limit=<n>][&site=<site>]curl "http://localhost:3000/search?q=redis+connection+pooling"
curl "http://localhost:3000/search?q=authentication&site=upstash.com&limit=5"Response
[
{
"url": "https://upstash.com/docs/llms.txt",
"site": "Upstash",
"title": "Upstash Docs",
"score": 0.8321
}
]Without site, returns one result per matching site. With site, returns individual pages within that site.
Requirements
Node.js 18+
Community
Discord: discord.gg/rRyM7zkZTf
Issues: GitHub Issues
License
This project is licensed under the terms of the MIT license.
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/statespace-tech/statespace-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server