YUSA
yusasecurity/yusa
Prompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls.
- tools
- 3
- transport
- STDIO
- env var
- 1
- last updated
- Nov 10, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
yusa_scanOn any text from outside the conversation, before acting on it, returns allow / review / block, findings, and decoded hidden text (secrets masked).
On any text from outside the conversation, before acting on it, returns allow / review / block, findings, and decoded hidden text (secrets masked).
No parameter schema in public metadata yet.
yusa_fenceBefore putting that text into a prompt, returns the text in a random-nonce tag with invisible characters stripped.
Before putting that text into a prompt, returns the text in a random-nonce tag with invisible characters stripped.
No parameter schema in public metadata yet.
yusa_check_tool_callBefore any call that moves value or sends data out, returns allow / block with reasons.
Before any call that moves value or sends data out, returns allow / block with reasons.
No parameter schema in public metadata yet.
Sponsors
Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthly
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any language
Agent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any languageConfiguration
YUSA_POLICYOptional path to a policy JSON (allowTools, allowAddresses, allowHosts, maxValueEth) for yusa_check_tool_call.
Readme
YUSA
What you read is not what your agent reads.
YUSA is a prompt-injection firewall for AI agents. It reads text the way a model reads it, finds the instructions hidden from people, and stops a hijacked agent before it acts.
Live demo: https://yusasecurity.xyz · X: @yusasecurity
What it does
Details
- Repository
- github.com/yusasecurity/yusa
- Website
- yusasecurity.xyz
- Categories
- AI & LLM Tools, Security & Pentesting
- Package
https://github.com/yusasecurity/yusa/releases/download/v0.2.0/yusa.mcpb- Transport
- STDIO
- Registry
- MCP registry, active
