OpenAI Agents MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_TRANSPORT | No | Transport protocol to use | stdio |
| OPENAI_API_KEY | Yes | Your OpenAI API key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_search_agentB | Use an AI agent specialized in web searching to find accurate, up-to-date information from the internet. |
| file_search_agentC | Use an AI agent specialized in searching through files and documents to find relevant information. |
| computer_action_agentC | Use an AI agent specialized in performing computer actions safely and effectively. |
| multi_tool_agentC | Use an AI agent that can orchestrate between web search, file search, and computer actions based on your query. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
The tools have mostly distinct purposes with clear specialization: computer actions, file search, web search, and a multi-tool orchestrator. However, the multi_tool_agent overlaps with the specialized agents by potentially performing their functions, which could cause some confusion about when to use it versus the specific agents.
All tool names follow a consistent snake_case pattern with a clear '_agent' suffix (e.g., computer_action_agent, file_search_agent). The naming is predictable and uniform across all four tools, making them easy to identify and categorize.
With 4 tools, the count is reasonable for an agent orchestration server, covering core areas like computer actions, file search, web search, and multi-tool coordination. It is slightly thin but well-scoped, as each tool serves a distinct role without unnecessary bloat.
The tool set covers key agent functionalities (computer actions, file search, web search, and orchestration), but there are notable gaps. For example, there is no dedicated tool for database operations, API interactions, or other common agent tasks, which might limit coverage for broader use cases in the agent domain.