# Boyce

> Use this tool when you need to compile natural language into deterministic SQL queries for AI agent database workflows, solving issues with query inconsistency and safety. It takes natural language inputs and produces standardized SQL outputs, utilizing a structured filter kernel and live schema inspection. Ideal for use cases requiring reliable and explainable database interactions, such as data analysis and reporting workflows.

Canonical page: https://skillsregistry.net/skills/boyce  
JSON: https://api.skillsregistry.net/v1/skills/boyce

## Description

Boyce is a deterministic SQL compiler and safety layer for AI agent database workflows. It converts natural language to SQL using a structured filter kernel — not LLM generation — so the same input always produces the same query. It includes live PostgreSQL/Redshift schema inspection, EXPLAIN pre-flight checks, and a NULL trap detector. Available on PyPI.

## Trust

- **Trust score (0–1):** 0.18
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/boyce)
- **Repository:** <https://github.com/boyce-io/boyce>

## 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": "boyce"
    }
  }
}
```

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