openai · OpenAI Platform Docs
Agents Integrations and observability
Teaches how to integrate external surfaces into an agent loop using Model Context Protocol (MCP) and how to implement observability through built-in tracing for debugging and evaluation.
Derived skill
Files assembled from official documentation
Viewing SKILL.md
Agents Integrations and observability
Teaches how to integrate external surfaces into an agent loop using Model Context Protocol (MCP) and how to implement observability through built-in tracing for debugging and evaluation.
When To Use
Use when deciding whether to host MCP tools in the SDK or connect to local servers, or when setting up tracing to inspect model calls, tool outputs, and handoffs during agent execution.
Reference Files
| File | Contains | Use For |
|---|---|---|
SKILL.md | Entry point: scope, routing table, and workflow. | Start here. |
docs/agents-integrations-observability-and-workflow-guide.md | A guide detailing how to integrate external surfaces into the agent loop and implement runtime inspection for observability. | Questions about a guide detailing how to integrate external surfaces into the agent loop and implement runtime inspection for observa... |
examples/agents-integrations-observability-and-openai-agents-typescript-integrati.typescript | A TypeScript code example demonstrating how to initialize an OpenAI Agent with hosted MCP tools for integration and observability. | Exact payloads, commands, or snippets shown in A TypeScript code example demonstrating how to initialize an OpenAI Agent with hosted MCP tools for integration and o... |
examples/agents-integrations-observability-and-openai-agents-mcp-hosted-tool.python | A Python code example demonstrating how to integrate an Agent with a HostedMCPTool using the OpenAI agents library. | Exact payloads, commands, or snippets shown in A Python code example demonstrating how to integrate an Agent with a HostedMCPTool using the OpenAI agents library. |
examples/agents-integrations-observability-and-openai-agents-mcp-filesystem-types.typescript | A TypeScript example demonstrating how to integrate an OpenAI Agent with a Filesystem MCP server using the @openai/agents library. | Exact payloads, commands, or snippets shown in A TypeScript example demonstrating how to integrate an OpenAI Agent with a Filesystem MCP server using the @openai/ag... |
examples/agents-integrations-observability-and-openai-agents-mcp-filesystem.python | A Python script demonstrating how to integrate an OpenAI Agent with a Model Context Protocol (MCP) filesystem server using asyncio. | Exact payloads, commands, or snippets shown in A Python script demonstrating how to integrate an OpenAI Agent with a Model Context Protocol (MCP) filesystem server... |
examples/agents-integrations-observability-and-openai-agents-typescript-integrati-2.typescript | A TypeScript code example demonstrating how to use the OpenAI Agents SDK to run a joke generator workflow wrapped in a trace for observability. | Exact payloads, commands, or snippets shown in A TypeScript code example demonstrating how to use the OpenAI Agents SDK to run a joke generator workflow wrapped in... |
examples/agents-integrations-observability-and-openai-agents-integrations-observa.python | A Python script demonstrating how to use the trace function to monitor agent workflows and runner execution. | Exact payloads, commands, or snippets shown in A Python script demonstrating how to use the trace function to monitor agent workflows and runner execution. |
What This Skill Covers
- After the workflow shape is clear, the next questions are which external surfaces should live inside the agent loop and how you will inspect what actually ha...
- Main sections:
Choose what lives in the SDK,MCP,Tracing,Next steps.
Workflow
- Open the most relevant file under
docs/for the exact documented workflow and wording. - Open
schemas/files for exact structured contracts. - Open
examples/files for concrete requests, commands, snippets, and manifests. - Do not add behavior or configuration that is not present in the attached source files.
Canonical source: https://developers.openai.com/api/docs/guides/agents/integrations-observability.md