---
format: "aidr-story-markdown/v1"
id: "b9513973bf250cd3fd4d1a68f6643d647a16f0658f6ed40cb8ca32f791b74109"
canonical_url: "https://aidr.today/b9513973?lang=en"
title: "Show HN: Conduct, open-source guardrails for LLM and MCP tool calls"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-08-28T19:29:20.000Z"
category: "Infra"
topics: ["open-source","llm","mcp","agent","safety"]
source_urls: ["https://github.com/sseshachala/conductai","https://news.ycombinator.com/item?id=49483173"]
summary: "AI agent governance for teams. Runtime firewalls tell you what happened; Conduct Guard controls what can happen — signed policy, verified chain, fail-closed by default. Ships with Router (LLM proxy..."
---

# Show HN: Conduct, open\-source guardrails for LLM and MCP tool calls

> [Open the canonical story](<https://aidr.today/b9513973?lang=en>)

**Published:** 2026-08-28T19:29:20.000Z
**Category:** Infra
**Topics:** open\-source, llm, mcp, agent, safety

## Summary

AI agent governance for teams\. Runtime firewalls tell you what happened; Conduct Guard controls what can happen — signed policy, verified chain, fail\-closed by default\. Ships with Router \(LLM proxy\.\.\.

## Sources

- [Story source](<https://github.com/sseshachala/conductai>)
- [Discussion](<https://news.ycombinator.com/item?id=49483173>)