# evidence-gate

> evidence-gate — lopezdray-evidence-gate. Use this tool when you need to ensure the accuracy of AI-generated content by grounding it in actual data, preventing the fabrication of facts. Evidence-gate solves the problem of AI models making up information by providing a pre-generation check, verifying the validity of statements against available data. It integrates with LLM/RAG applications, offering a lightweight, dependency-free solution with support for JavaScript, Python, and an MCP server.

Canonical page: https://skillsregistry.net/skills/lopezdray-evidence-gate  
JSON: https://api.skillsregistry.net/v1/skills/lopezdray-evidence-gate

## Description

Stop your AI from making up facts about your own data. A pre-generation grounding gate for LLM/RAG apps — zero-dep, MIT, JS + Python, with an MCP server.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/LopezDray/evidence-gate)

## 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": "lopezdray-evidence-gate"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lopezdray-evidence-gate` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lopezdray-evidence-gate/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