# OpenXAI MCP Server

> Use this tool when you need to evaluate and benchmark AI explanation methods for transparency and reliability. It solves problems of assessing AI model trustworthiness and comparing explanation techniques through a standardized interface. The OpenXAI MCP Server takes in AI models and explanation methods as inputs and outputs benchmarking results, making it ideal for use cases requiring rigorous AI model testing and validation.

Canonical page: https://skillsregistry.net/skills/cappybara12-mcpopenxai  
JSON: https://api.skillsregistry.net/v1/skills/cappybara12-mcpopenxai

## Description

Provides tools for evaluating and benchmarking AI explanation methods through a standard interface that can be used with AI assistants and MCP-compatible applications.

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/xrmckpndbc)
- **Repository:** <https://github.com/Cappybara12/mcpopenxAI>

## 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": "cappybara12-mcpopenxai"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cappybara12-mcpopenxai` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cappybara12-mcpopenxai/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