# Midplane

> Midplane — midplaneai-midplane. Use this tool when you need to protect your Postgres database from unintended or malicious queries executed by AI agents. Midplane enforces policies, blocks destructive queries, and audits all access, providing a secure interface between AI agents and your database. It takes SQL queries as input and outputs audited, policy-compliant queries, ensuring secure and controlled database interactions.

Canonical page: https://skillsregistry.net/skills/midplaneai-midplane  
JSON: https://api.skillsregistry.net/v1/skills/midplaneai-midplane

## Description

SQL guardrails for AI agents, sitting between the agent and Postgres to enforce policies, block destructive queries, and audit all access.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/esqypy61gq)
- **Repository:** <https://github.com/midplaneai/midplane>

## 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": "midplaneai-midplane"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/midplaneai-midplane` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/midplaneai-midplane/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