cd /news/ai-safety/mcp-needs-an-approval-button · home topics ai-safety article
[ARTICLE · art-21771] src=simianwords.bearblog.dev pub= topic=ai-safety verified=true sentiment=· neutral

MCP Needs an Approval Button

The Model Context Protocol (MCP) lacks a cryptographically verified human approval mechanism, leaving systems vulnerable to unauthorized changes. Without a mandatory approval button, agents can execute irreversible actions like purchasing tickets, deleting folders, destroying databases, or approving pull requests without user consent.

read1 min publishedJun 4, 2026

MCP is cool but it needs a verified human in the loop approval button. Here's what I mean in a picture.

The reason this is important is because there must be a cryptographically verified way for the server to guarantee that it showed you the payload and that you the human have approved it.

If the MCP is set up in such a way that the specific method is gated behind human, there is no way for the agent to make changes on your behalf no matter how hard it tries.

Examples of what can be achieved

  • transactions like purchasing flight tickets
  • irreversible changes to a system like say deleting some folder
  • destroying an DynamoDb table
  • approving a Github PR
── more in #ai-safety 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/mcp-needs-an-approva…] indexed:0 read:1min 2026-06-04 ·