OpenAI Agents
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.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/lroolle/openai-agents-mcp-server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve OpenAI Agents from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.