# nlqdb — analytical memory for AI agents

Connects an AI agent to a database over MCP so it can answer analytical questions in plain English. Useful when database work should stay inside the coding workflow.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 2
- Author: nlqdb
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/nlqdb/nlqdb
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/nlqdb-analytical-memory-for-ai-agents

## What it does

nlqdb connects an AI agent to its hosted MCP server and lets the agent query a database in plain English. It works with Postgres and Cloudflare D1: the response includes the SQL that ran and a confidence signal, so the generated answer can be checked.

Claude Code can connect over HTTP, while Codex, Cursor, GitHub Copilot, and Gemini CLI have their own setup forms. A headless MCP host can run `npx -y @nlqdb/mcp` with an `sk_mcp_*` key; other hosts use browser OAuth approval.

Natural-language-to-SQL results can still be wrong. Check the SQL and confidence signal before relying on an answer, especially when the query informs a database decision.

## Requirements
- Remote server: `https://mcp.nlqdb.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http nlqdb https://mcp.nlqdb.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add nlqdb-analytical-memory-for-ai-agents --url https://mcp.nlqdb.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "nlqdb-analytical-memory-for-ai-agents": {
            "url": "https://mcp.nlqdb.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "nlqdb-analytical-memory-for-ai-agents": {
            "type": "http",
            "url": "https://mcp.nlqdb.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http nlqdb-analytical-memory-for-ai-agents https://mcp.nlqdb.com/mcp
```

## When to use it
- connect an AI agent to a database over MCP
- ask analytical questions in plain English
- inspect the SQL produced for an answer
- check confidence for a generated result
- run the local MCP server on a headless host

## Example prompts
- Ask the database for the 5 newest orders and include their customers and items.
- Show the SQL used for this order analysis and report the confidence signal.
- Connect to the database over MCP and find records matching this condition.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md