# frontendmcp

> frontendmcp — failip-frontendmcp. Use this tool when you need to establish a lightweight and efficient communication channel between frontend MCP servers and backend Large Language Models (LLMs) via WebSockets. It solves the problem of exposing MCP servers to LLMs, enabling seamless interaction and data exchange. The frontendmcp tool takes in MCP server inputs and outputs WebSocket-compatible data for backend LLMs to consume.

Canonical page: https://skillsregistry.net/skills/failip-frontendmcp  
JSON: https://api.skillsregistry.net/v1/skills/failip-frontendmcp

## Description

A lightweight WebSocket relay and transport layer to run Model Context Protocol (MCP) servers in the browser and expose them to backend LLMs.

## Trust

- **Trust score (0–1):** 0.80
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/failip/frontendmcp)

## 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": "failip-frontendmcp"
    }
  }
}
```

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