# mcpscope

> mcpscope — ffleurey-mcpscope. Use this tool when you need to build, inspect, and benchmark MCP servers against local or remote Large Language Models (LLMs). It solves problems related to testing and optimizing MCP server performance, providing a local-first workbench with Web UI, CLI, and MCP interface. Ideal for use cases involving LM Studio, Ollama, or OpenRouter, where you need to integrate an embeddable TypeScript agent runtime with zero dependencies.

Canonical page: https://skillsregistry.net/skills/ffleurey-mcpscope  
JSON: https://api.skillsregistry.net/v1/skills/ffleurey-mcpscope

## Description

Local-first workbench to build, inspect & benchmark MCP servers against local or remote LLMs (LM Studio · Ollama · OpenRouter) — Web UI, CLI & MCP interface. Ships mcpscope-engine: an embeddable, zero-dependency TypeScript agent runtime.

## Trust

- **Trust score (0–1):** 0.68
- **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/ffleurey/mcpscope)

## 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": "ffleurey-mcpscope"
    }
  }
}
```

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