zn-gate

MCPattested
v1.8.2useznMITUpdated todaynpmGitHub

Local security layer for coding agents (Claude Code, Codex CLI, Cursor, OpenCode): keeps secrets out of what the agent sends to the model, checks for prompt injection and guards the MCP servers you wrap.

Works in
ClaudeCursorCopilotGemini

Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Attested build
A verified provenance attestation binds this artifact to the listed repository. Nobody has claimed the listing yet — this proves where the code was built, not who stands behind it.
506Downloads/wk
2GitHub stars
todayLast update
Reads these credentials
  • ZN_API_KEYAPI keyoptional

    API key for the optional cloud check. Has no effect without ZN_CLOUD=1.

Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.

Package
Authorusezn
LicenseMIT
Version1.8.2
Sourcenpm+mcp-registry
npmzn-gate
GitHubusezn/zn
SBOMCycloneDX 1.6 ↓
Trust Status
A
85/100Trusted
✓Listed in Forge index+10/10
✓Identity verified · attested build+20/20
—Ed25519 publish signature+0/5
→ 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>" }
✓npm Trusted Publishing (Sigstore)+5/5
—npm maintainer match+0/5
→ Publisher: add the verified GitHub login to the npm package's maintainers (npm owner add <login>)
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusIdentity verified
PublisherUnverified
SignatureUnsigned
Domain—
Provenance✓ Sigstore-verified · 0d78201
Dependencies✓ 8 resolved · none vulnerable
Tool surface20 tools · 2 privileged
Security scan✓ Cleanv1.9.0 · todayHow well does this scan work?
EvalsNone
IndexedOct 16, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

20 tools · 2 privileged
Statically extracted from the published packagev1.9.0 · 4h ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

auto-run-commandprivilegedNo description published

This tool published no description. Forge does not invent one.

download-and-runNo description published

This tool published no description. Forge does not invent one.

project-mcp-commandprivilegedNo description published

This tool published no description. Forge does not invent one.

mcp-auto-approveNo description published

This tool published no description. Forge does not invent one.

unpinned-packageNo description published

This tool published no description. Forge does not invent one.

remote-mcpNo description published

This tool published no description. Forge does not invent one.

endpoint-overrideNo description published

This tool published no description. Forge does not invent one.

code-loading-envNo description published

This tool published no description. Forge does not invent one.

credential-helperNo description published

This tool published no description. Forge does not invent one.

broad-permissionsNo description published

This tool published no description. Forge does not invent one.

secret-in-configNo description published

This tool published no description. Forge does not invent one.

instruction-injectionNo description published

This tool published no description. Forge does not invent one.

instruction-download-runNo description published

This tool published no description. Forge does not invent one.

instruction-exfiltrationNo description published

This tool published no description. Forge does not invent one.

instruction-weaken-checksNo description published

This tool published no description. Forge does not invent one.

shadowing-executableNo description published

This tool published no description. Forge does not invent one.

project-pluginsNo description published

This tool published no description. Forge does not invent one.

agent-extensionsNo description published

This tool published no description. Forge does not invent one.

ci-agent-untrusted-inputNo description published

This tool published no description. Forge does not invent one.

unchecked-agent-fileNo description published

This tool published no description. Forge does not invent one.

0 of 20 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

Local security layer for coding agents (Claude Code, Codex CLI, Cursor, OpenCode): keeps secrets out of what the agent sends to the model, checks for prompt injection and guards the MCP servers you wrap.

Keywords
prompt-injectionmcpmodel-context-protocolai-securityllm-guardrailsai-agentssecurity-proxycursorclaude-codeopencodecodex
Alternatives
Comparing tool surfaces…

Tools exposed

20 tools · 2 privileged · observed by static extraction. A tool surface is what one scan read on one day, not a live capability list.

Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.

Dependency tree

What one Forge scan resolved from npm metadata on 2026-10-16 — observed resolution, not a publisher declaration.

8 packages resolved · 1 direct · none carrying advisories Resolution stops at depth 4 and 60 packages.

Topics

Related in security