Authorize MCP tool calls without giving agents the credentials
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Hey HN, Adam here.We built a small MCP example around a single problem:How do you let an agent use a tool that needs credentials without giving the credentials to the agent?The demo has two tools. One is open. One is protected.When the agent calls the protected tool, Keydris checks the policy first:ALLOW ā run the tool REJECT ā stopThe credential stays on the server. The agent never sees it.We do the check through a small middleware on the MCP server called the KIT Reader.Repo: https://github.com/keydrisLabs/mcp-auth-keydris-templateWe're early. If you're building with MCP, Claude Code or Codex, I'd love to know how you're handling this today and where you think this approach breaks.We support other elements like integrations etc but would love your feedback
HN · launched Sep 14, 2026 · 7 upvotes (top 56%) · 0 views
Niche: ai agent security and monitoring tools · 297 launches, 14 in the last 7 days ▼ -44% · Explore this niche →
Category and tags
- Horizontal
- Compliance & governance
- Developer
- AI-native
- Commercial product
Visit website ↗ Source listing ↗
More like this: all 297 launches in ai agent security and monitoring tools →
Could you build this?
Yes This is an authorization proxy demo for MCP tools that validates requests against a policy engine before injecting stored credentials and calling downstream APIs.
Discussion
6 comments analyzed.
Competitors mentioned: runjs, 1Claw, Dome Systems
Concerns raised: exposure of long-lived keys if server is compromised
Feature requests: integration with centralized SIEM and log collection, short-lived key issuance
Competitors
Other products that read as similar to this one : 517 launches clear the similarity bar, closest 8 shown.
Attention rank: #270 of 518 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 306 days after the earliest competitor.
- TotalHeal AgentGate · ph · 2026-11-10 · 1 upvotes · similarity 0.57
- SafeGen · ph · 2026-09-15 · 3 upvotes · similarity 0.57
- Buddy AI Access (MCP) · ph · 2026-09-15 · 99 upvotes · similarity 0.56
- Agent Middleware · ph · 2026-10-13 · 1 upvotes · similarity 0.52
- mcp-auth-keydris-template · github · 2026-09-14 · 6 upvotes · similarity 0.50
- squidbrake · github · 2026-09-29 · 11 upvotes · similarity 0.50
- cMCP, deny an AI agent's tool call and get a signed receipt · hn · 2026-08-04 · 9 upvotes · similarity 0.49
- Guard Starter · ph · 2026-09-25 · 1 upvotes · similarity 0.49
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.