guardrail-mcp

MCPcommunity
v1.0.2io.github.rudimentall1UnknownUpdated 5d agoGitHub

Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
5d agoLast update
Package
Authorio.github.rudimentall1
LicenseUnknown
Version1.0.2
Sourcemcp-registry
GitHubrudimentall1/agent-guardrail
Trust Status
F
10/100Untrusted
✓Listed in Forge index+10/10
—Publisher identity verified+0/30
→ Publisher: run `forge publish` from the repo to claim ownership
—Domain verification+0/10
→ Publisher: host /.well-known/forge.json on the project homepage with { "publisher": "<github-login>" }
—Prompt-injection scan · not run+0/30
→ This entry exposes no inspectable source (a hosted endpoint), so there is nothing to scan. Publish an npm package or link a public repository to become scannable.
—Obfuscation / exfil scan · not run+0/20
→ This entry exposes no inspectable source (a hosted endpoint), so there is nothing to scan. Publish an npm package or link a public repository to become scannable.
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
DependenciesNot audited
Tool surface—
Security scanNot run
EvalsNone
IndexedAug 11, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.

About

Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.

Keywords
mcp