Authorize MCP tool calls without giving agents the credentials
Authorize MCP tool calls without giving agents the credentials
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 → run the tool REJECT → stop The 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-template We'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
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Correct prediction on native model
Similar products
Authorize MCP tool calls without giving agents the credentials
VellaVeto — blocks unsafe MCP tool calls by default
A2A <=> MCP Agents
Cordon – Security gateway for MCP tool calls with HITL approvals
Do you suck at delivering presentations or giving pitches?
mcp-chat, chat server using MCP tool calls
I'm giving away my MicroSaaS
Crowdfunding platform for aid supplies
I made an challenge giving app so that you no longer get bored
A new social giving platform