# MCPBench

> MCPBench — modelscope-mcpbench. Use this tool when you need to evaluate the performance of MCP servers, solving problems related to server assessment and optimization. It provides a benchmarking framework that takes input from MCP server configurations and outputs performance metrics, allowing for informed decisions on server upgrades and resource allocation. Ideal for use cases involving server evaluation, comparison, and tuning, MCPBench streamlines the assessment process through its integration with git.

Canonical page: https://skillsregistry.net/skills/modelscope-mcpbench  
JSON: https://api.skillsregistry.net/v1/skills/modelscope-mcpbench

## Description

The evaluation benchmark on MCP servers

## Trust

- **Trust score (0–1):** 0.53
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/modelscope/MCPBench)

## 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": "modelscope-mcpbench"
    }
  }
}
```

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