# AgentGrade

> Use this tool when you need to assess a website's compatibility with AI agents or ensure seamless interaction between agents and online services. AgentGrade scans websites for payment protocol compliance, MCP discovery endpoints, and agent-accessible APIs, identifying areas for improvement. It returns structured scores and recommendations to enhance agent compatibility, streamlining the process of making services accessible to AI agents.

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

## Description

AgentGrade scans websites to assess their readiness for AI agent interaction, checking for payment protocol compliance, MCP discovery endpoints, and agent-accessible APIs. Returns structured scoring and recommendations for making services agent-compatible.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** finance
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/agentgrade)

## 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": "agentgrade"
    }
  }
}
```

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