nexus-mcp
Server Details
Japanese LLM security — prompt injection detection (jpi-guard) + PII masking (PII Guard). Free.
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over 42 days
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- nexus-api-lab/nexus-mcp
- GitHub Stars
- 0
- Server Listing
- nexus-mcp
TDQS
Scored across 6 tools
Most tools have distinct purposes, but there is some overlap between check_injection, sanitize_content, and validate_rag_input, as all three involve prompt injection detection for Japanese content. However, their specific focuses (detection vs. sanitization vs. validation) and descriptions help differentiate them, preventing major confusion.
Tool names follow a consistent verb_noun pattern (e.g., check_injection, get_pii_guard_key, pii_scan), with only sanitize_content slightly deviating by using a verb_adjective format. Overall, the naming is predictable and readable, with minor inconsistency.
With 6 tools, the server is well-scoped for its purpose of Japanese-language content security and PII handling. Each tool serves a clear role, such as injection detection, PII scanning, and API key management, making the count appropriate without being excessive or insufficient.
The tool set provides comprehensive coverage for the domain of Japanese content security, including injection detection, sanitization, validation, PII scanning, and API key acquisition for related services. There are no obvious gaps, as it supports the full workflow from input validation to content processing.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
4 tool updates
- Changed
check_injection1 field changed- changed
Input schema / properties / api_key / descriptionPrevious value: -"Your jpi-guard API key. Get a free trial at https://jpi-guard.nexus-api-lab.workers.dev/"New value: +"Your jpi-guard API key. If you don't have one, call get_trial_key first to get a free key instantly."
- Changed
pii_scan1 field changed- changed
Input schema / properties / api_key / descriptionPrevious value: -"Your PII Guard API key (format: pii_<32hex>). Get a free key with get_pii_guard_key or at https://www.nexus-api-lab.com/pii-guard.html"New value: +"Your PII Guard API key (format: pii_<32hex>). If you don't have one, call get_pii_guard_key first to get a free key instantly."
- Changed
sanitize_content1 field changed- changed
Input schema / properties / api_key / descriptionPrevious value: -"Your nexus-api-lab API key (Bearer token). Get a free trial key at https://www.nexus-api-lab.com"New value: +"Your nexus-api-lab API key (Bearer token). If you don't have one, call get_trial_key first to get a free key instantly."
- Changed
validate_rag_input1 field changed- changed
Input schema / properties / api_key / descriptionPrevious value: -"Your jpi-guard API key. Get a free trial at https://jpi-guard.nexus-api-lab.workers.dev/"New value: +"Your jpi-guard API key. If you don't have one, call get_trial_key first to get a free key instantly."
6 tool updates
- First observed
check_injection - First observed
get_pii_guard_key - First observed
get_trial_key - First observed
pii_scan - First observed
sanitize_content - First observed
validate_rag_input
Related MCP Connectors
The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
Responsible-AI guardrails for agents: scoring with policy, injection & PII detection, DPDP.
AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceSecurity middleware for LLM apps and AI agent pipelines. Detects prompt injection attacks (22 signatures, 7 languages) and anonymizes PII (17 entity types). Deterministic, sub-25ms, GDPR Art.30 compliant.-
- AlicenseBqualityBmaintenanceWAF for AI agents — block prompt injection before it reaches the LLM.593 PyPIMIT
- AlicenseNot gradedqualityDmaintenanceAnalyzes inputs and outputs in real-time to protect against prompt injections, data leaks, secrets exposure, and phishing URLs.35 npm3MIT
- AlicenseAqualityBmaintenanceProtects AI agents from threats like prompt injection, jailbreaks, and SQL injection through a multi-layer scanning pipeline. It also enables PII redaction and rehydration to ensure data privacy during LLM interactions.12108 npm2Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.