little-canary MCP Server
hermes-labs-ai/little-canary
Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
hermes-labs-ai/little-canary is a Python tool licensed under Apache-2.0. Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
Ranked #6634 out of 24840 indexed tools.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
33 stars → early stage
Last commit today → actively maintained
0/3 issues closed → many open issues
7 contributors → small team
No dependents → no downstream usage
178 weekly installs → early adoption
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Badge all embed codes →
[](https://agentrank-ai.com/tool/hermes-labs-ai--little-canary/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/hermes-labs-ai--little-canary/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/badge/tool/hermes-labs-ai--little-canary" alt="AgentRank"></a> Matched Queries
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.