# mcp-databend

> Use this tool when you need to securely connect AI agents to Databend databases for experimentation and testing. It solves the problem of protecting production data by providing a session sandbox that keeps the database read-only. The tool accepts database credentials as input and outputs a secure, sandboxed connection for AI agents to interact with the database.

Canonical page: https://skillsregistry.net/skills/databendlabs-mcp-databend  
JSON: https://api.skillsregistry.net/v1/skills/databendlabs-mcp-databend

## Description

Enables AI agents to connect to Databend databases safely with a session sandbox that keeps production read-only while agents experiment.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-06-12

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/q9yrobzx4s)
- **Repository:** <https://github.com/databendlabs/mcp-databend>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "databendlabs-mcp-databend"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/databendlabs-mcp-databend` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/databendlabs-mcp-databend/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt