# mcp-llm-behave

> Use this tool when you need to perform offline behavioral regression testing on large language models (LLMs) to ensure semantic similarity in their outputs. It solves problems related to testing and validating LLMs without relying on API calls, providing a reliable and efficient way to check output consistency. The tool takes LLM outputs as input and returns semantic similarity checks as output, making it ideal for use cases where offline testing and validation are crucial.

Canonical page: https://skillsregistry.net/skills/swanand33-mcp-llm-behave  
JSON: https://api.skillsregistry.net/v1/skills/swanand33-mcp-llm-behave

## Description

Exposes llm-behave's behavioral regression testing as MCP tools, allowing offline semantic similarity checks on LLM outputs without any API calls.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/holnxo9cab)
- **Repository:** <https://github.com/Swanand33/mcp_llm_behave>

## 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": "swanand33-mcp-llm-behave"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/swanand33-mcp-llm-behave` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/swanand33-mcp-llm-behave/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