# oxe

> oxe — espetro-oxe. Use this tool when you need to optimize web searches for AI agents, providing a local cache and proxy to reduce latency and improve performance. It solves problems of slow search queries and high bandwidth usage, accepting HTTP API and MCP inputs and returning cached search results. Ideal for use cases where AI agents require fast and efficient access to web data, such as in resource-constrained environments.

Canonical page: https://skillsregistry.net/skills/espetro-oxe  
JSON: https://api.skillsregistry.net/v1/skills/espetro-oxe

## Description

Local web-search proxy and cache for AI agents. Exa-compatible HTTP API + MCP, under 30MB RSS.

## Trust

- **Trust score (0–1):** 0.08
- **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/espetro/oxe)

## 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": "espetro-oxe"
    }
  }
}
```

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