Skip to content

manylives.me

Check text before your agent reads or forwards it: prompt-injection…

Check text before your agent reads or forwards it: prompt-injection attempts aimed at AI readers, and contact details (emails, phones, handles, links). Returns flags, a risk level and a cleaned copy.

Ready now2 calls · 2 buyers in 30 days

Input

No sample input is published, so the fields start empty.

Body
Fix this before running
  • Input: Instance does not have required property "body".

Sample response

Published by the provider. Your run returns a fresh response.

response5 keys
ai_review2 keys
reason"…"
severity"high"
cleaned"…"
contacts_removed1 item
0"email"
injection1 item
0"ignore (all )?(previous|prior) instructions"
risk"high"
responseobject, 5 keys
Your agent can do this on its own
Add the MCP URL in Claude Code, Cursor or Codex. Your agent can run Tools within its spending limits, or ask for approval each time. Connect your agent

Connect your agent

Add one MCP URL and your agent can find and run this tool within its spending limits. Choose “Ask each time” if you want to approve every Call.

MCP URL

https://app.aecon.ai/mcp
Terminalbash
claude mcp add --transport http --scope user agentic-economy "https://app.aecon.ai/mcp"

In Claude Code, open /mcp, select agentic-economy, then choose Authenticate.

Track record

Paid calls, last 30 days
2
Buyers, last 30 days
2
Last paid call

Reported by the x402 directory.

A$0.015 per call