io.github.nexus-api-lab/nexus-mcp

MCPcommunity
v1.0.0io.github.nexus-api-labUnknownUpdated 2mo agoGitHub

Japanese LLM security — prompt injection detection (jpi-guard) + PII masking (PII Guard). Free.

LLM security APIs for Japanese applications, available as an MCP server. Transport: HTTP (Streamable HTTP / JSON-RPC 2.0) Add to your MCP config: After connecting, no API key is required to begin. Claude will call automatically: 1. Call to obtain a free API key (if not already set) 2. Call on the user input 4. Block the input if injection is detected 1. Call with the fetched content 2. Return…

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
2mo agoLast update
Package
Authorio.github.nexus-api-lab
LicenseUnknown
Version1.0.0
Sourcemcp-registry
GitHubnexus-api-lab/nexus-mcp
Trust Status
B
60/100Good
✓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 · not run+0/30
→ Not yet scanned — package must be on npm
✓Static analysis · clean+20/20
—npm provenance (Sigstore)+0/5
→ Publish from GitHub Actions with the --provenance flag
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
DependenciesNot audited
Tool surface—
Security scan✓ CleanvHEAD · 19d 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

LLM security APIs for Japanese applications, available as an MCP server. Transport: HTTP (Streamable HTTP / JSON-RPC 2.0) Add to your MCP config: After connecting, no API key is required to begin. Claude will call automatically: 1. Call to obtain a free API key (if not already set) 2. Call on the user input 4. Block the input if injection is detected 1. Call with the fetched content 2. Return with injection payloads removed 3. Use the cleaned version as LLM context 1. Call to obtain a free key…

Keywords
mcp