experimental-ext-interceptors / setup / openai-agents
Setup guide
Set up experimental-ext-interceptors in OpenAI Agents SDK
officialunknownofficialno verified config · noindex
Status: Experimental. This repository provides a multi-language reference implementation of the proposed interceptor extension for the Model Context Protocol (MCP), as described in SEP-2624.
01Configuration
# experimental-ext-interceptors via OpenAI Agents SDK
# transport: unknown
# launch: the server's install method
OpenAI Agents SDK connects to MCP servers in code. Use its MCP client with the command/URL below; exact API varies by version.
02Steps
- Make sure OpenAI Agents SDK is installed and up to date.
- Wire the server into OpenAI Agents SDK using its MCP client API.
- Provide any required API keys/credentials as environment variables.
- Restart OpenAI Agents SDK and confirm experimental-ext-interceptors’s tools appear.
03Other runtimes
04Provenance
config_sourcegenerated from captured install method
last_checked2026-07-16 14:14Z
sourcesGitHub repo search [p4]
Next step
Want agents that act within guardrails? Apex is the live governed-agent product — paced, capped, and fully-logged actions with approvals before anything runs.
Explore Apex →See also: server page · is it safe? · alternatives