# OpenAI Agents

> Use this tool when you need to access real-time information retrieval, document analysis, or safe computer automation within AI assistant conversations. It solves problems related to workflows requiring web search, file search, and computer actions by providing a multi-agent orchestrator that coordinates between specialized agents. With inputs including task requirements and outputs such as retrieved information or automated actions, it is ideal for use cases involving AI assistants that need to interact with computers or retrieve information in real-time.

Canonical page: https://skillsregistry.net/skills/lroolle-openai-agents  
JSON: https://api.skillsregistry.net/v1/skills/lroolle-openai-agents

## Description

OpenAI Agents MCP Server exposes OpenAI's agent capabilities through the Model Context Protocol, allowing AI assistants to access web search, file search, and computer actions. Built by Eric Wang, it implements both specialized agents for individual tools and a multi-agent orchestrator that can coordinate between them based on the task requirements. The server uses FastMCP to handle communication, supports both stdio and SSE transports, and includes a simulated computer interaction mode that can be extended for real-world actions. Particularly valuable for workflows requiring real-time information retrieval, document analysis, or safe computer automation within AI assistant conversations.

## Trust

- **Trust score (0–1):** 0.94
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/lroolle-openai-agents)
- **Repository:** <https://github.com/lroolle/openai-agents-mcp-server>

## 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": "lroolle-openai-agents"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lroolle-openai-agents` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lroolle-openai-agents/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