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

Agent Boundary

by · github.com/impactRssi/agent-boundary

A deterministic tool-call broker that bounds what an LLM agent can actually do. Indirect prompt injection is assumed to succeed; authorisation lives outside the model.

Unclaimed ai-agentsappsecdevsecopsllm-securitymcpprompt-injectionpythonthreat-modeling
InstallView source
34Low

Scored 14 days ago · breakdown

About Agent Boundary

Agent Boundary is an MCP server published by impactRssi in the Science category: a deterministic tool-call broker that bounds what an LLM agent can actually do. Indirect prompt injection is assumed to succeed; authorisation lives outside the model.

Install

From source
git clone https://github.com/impactRssi/agent-boundary

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 Boundary

Powered by Claude · Grounded in docs

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

Security checks

6 checks have not been run yet.

Questions

About Agent Boundary

How do I install Agent Boundary?

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

Is Agent Boundary 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 Boundary still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.