# relay-mcp

> relay-mcp — arclat-ai-relay-mcp. Use this tool when you need to identify and resolve latency issues in AI agent and voice-agent codebases. The relay-mcp tool audits and optimizes code for faster performance, taking in git repositories as input and outputting verified and fixed latency bottlenecks. It is ideal for use cases where minimizing AI agent latency is crucial, such as real-time voice interactions or time-sensitive decision-making applications.

Canonical page: https://skillsregistry.net/skills/arclat-ai-relay-mcp  
JSON: https://api.skillsregistry.net/v1/skills/arclat-ai-relay-mcp

## Description

Relay - open-source AI agent latency auditor. A local MCP server + CLI that finds, verifies, and fixes latency bottlenecks in AI agent and voice-agent codebases. No API key, no backend.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/arclat-ai/relay-mcp)

## 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": "arclat-ai-relay-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/arclat-ai-relay-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/arclat-ai-relay-mcp/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