# coralquery-mcp

A hosted remote MCP server for querying data through AI SDK. It returns structured results, usage receipts, and audit evidence.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: clauxel
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/clauxel/coral-query-plane-mcp
- Updated: 2026-05-25
- HTML: https://affpapa.org/en/nevibecode/mcp/coralquery-mcp

## What it does

coralquery-mcp connects an AI agent to a hosted remote MCP endpoint for data queries. Its tool set includes `source_list`, `query_run`, `schema_preview`, and `result_receipt`, covering source discovery, query execution, schema inspection, and result confirmation.

The service uses Streamable HTTP and exchanges structured JSON. Production requests require a bearer token issued after choosing a plan and creating or requesting an API token. Without that token, production calls will fail. The server can be connected from Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, and Gemini CLI.

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

## Install

### Claude Code (native platform)

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

### Codex

**Platform CLI: remote server**
```bash
codex mcp add coralquery-mcp --url https://coralquery.clauxel.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "coralquery-mcp": {
            "url": "https://coralquery.clauxel.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "coralquery-mcp": {
            "type": "http",
            "url": "https://coralquery.clauxel.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http coralquery-mcp https://coralquery.clauxel.com/mcp
```

## When to use it
- list accessible data sources
- run a query against a selected source
- inspect a source schema
- retrieve a query result receipt
- capture evidence for an agent workflow

## Example prompts
- Use `source_list` to show the data sources I can query.
- Run a query against the selected source with `query_run` and return the result.
- Inspect the source schema, then create a result receipt with `result_receipt`.

## Similar
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89609
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89899
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40459
- [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27844
- [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49863

---
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