# mcpgrade

> mcpgrade — tengbyte-mcpgrade. Use this tool when you need to evaluate the usability of MCP servers for AI agents, assessing factors like description quality and schema design to determine their effectiveness. It grades servers on a scale of A to F, providing a benchmark for comparison across different servers. Ideal for identifying and optimizing servers to improve model performance and tool selection accuracy.

Canonical page: https://skillsregistry.net/skills/tengbyte-mcpgrade  
JSON: https://api.skillsregistry.net/v1/skills/tengbyte-mcpgrade

## Description

Grades MCP servers on agent usability (A–F) — description quality, schema design, tool naming and token cost, the properties that decide whether a model picks the right tool. Benchmarked across 36 popular servers; a third scored D or F.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/jr9ma1v40s)
- **Repository:** <https://github.com/TengByte/mcpgrade>

## 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": "tengbyte-mcpgrade"
    }
  }
}
```

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