1. Conduid
  2. Science
  3. Agent Cordon
MCP server · Science

Agent Cordon

by · github.com/adibhatt1997/agent-cordon

Zero-dependency prompt-injection and data-exfiltration firewall for LLM agents: scans untrusted text and outbound actions, sees through obfuscation, guards the MCP/tool boundary.

Unclaimed agentsai-safetyai-securityguardrailsjailbreakllmllm-guardrailsllm-securitymcpprompt-engineeringprompt-injectionpythonsecurity
InstallView source
34Low

Scored 8 hours ago · breakdown

About Agent Cordon

Agent Cordon is an MCP server published by adibhatt1997 in the Science category: zero-dependency prompt-injection and data-exfiltration firewall for LLM agents: scans untrusted text and outbound actions, sees through obfuscation, guards the MCP/tool boundary.

Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/adibhatt1997/agent-cordon

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Agent Cordon

Powered by Claude · Grounded in docs

I know everything about Agent Cordon. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About Agent Cordon

How do I install Agent Cordon?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Agent Cordon safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Agent Cordon still maintained?

Yes — the last commit was 3 months ago. The repository has 0 stars and 0 forks.