io.github.IgorGanapolsky/thumbgate

MCPcommunity
v1.23.2io.github.IgorGanapolskyUnknownUpdated 1mo agonpmGitHub

Pre-action gates that block AI agents from repeating known mistakes.

AI coding agents repeat mistakes — and one wrong tool call can wipe a directory, leak a key, or push broken code. ThumbGate is the local-first firewall for AI coding agents. It runs in the PreToolUse hook on your machine and blocks dangerous tool calls — , secret exfiltration, off-scope edits, a bad — before they execute, across Claude Code, Cursor, Codex, Gemini, Amp, Cline, and OpenCode. No…

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
1mo agoLast update
Package
Authorio.github.IgorGanapolsky
LicenseUnknown
Version1.23.2
Sourcemcp-registry
npmthumbgate
GitHubIgorGanapolsky/ThumbGate
Trust Status
A
95/100Trusted
✓Listed in Forge index+10/10
—Publisher identity verified+0/25
→ Publisher: run `forge publish` from the package repo to claim ownership
—Ed25519 publish signature+0/10
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
✓npm provenance (Sigstore)+5/5
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance✓ Sigstore-verified · b1e0d7c
Dependencies✓ 60 resolved+ · none vulnerable
Tool surface40 tools · 3 privileged
Security scan✓ Cleanv1.27.6 · 20d ago
EvalsNone
IndexedJun 13, 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

AI coding agents repeat mistakes — and one wrong tool call can wipe a directory, leak a key, or push broken code. ThumbGate is the local-first firewall for AI coding agents. It runs in the PreToolUse hook on your machine and blocks dangerous tool calls — , secret exfiltration, off-scope edits, a bad — before they execute, across Claude Code, Cursor, Codex, Gemini, Amp, Cline, and OpenCode. No server, no gateway. (Regulated-industry policy templates — legal intake, financial compliance,…

Keywords
mcp