MCP Radar
MCP-Server

ai-guardrails

io.github.lazymac2x/ai-guardrails
Sicherheit Öffentlich und erreichbar MCP 2026-07-28

Was dieses MCP kann

Detects and redacts PII, checks text for harmful content, and applies heuristic hallucination-risk checks.

Funktionen

Tools

5 Tools
check_hallucination
Heuristic scoring of LLM hedge phrases that correlate with hallucinated outputs. Returns score 0–1 and risk level.
Eingabeschema 
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string'}}}
check_safety
Check text for harmful content using weighted keyword detection. Returns a 0–1 score and verdict (safe/caution/unsafe).
Eingabeschema 
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string'}}}
detect_pii
Detect personally identifiable information (email, phone, SSN, credit card, IP, URL, API key) in a text string.
Eingabeschema 
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'description': 'Text to scan for PII'}}}
full_check
Run pii, safety, and/or hallucination checks in one call. Default: pii + safety. Specify checks=["pii","safety","hallucination"] to run all.
Eingabeschema 
{'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string'}, 'checks': {'type': 'array', 'items': {'enum': ['pii', 'safety', 'hallucination'], 'type': 'string'}, 'default': ['pii', 'safety']}}}
redact_pii
Redact PII from text. mode=mask replaces with [REDACTED]; mode=tag uses typed placeholders like [EMAIL].
Eingabeschema 
{'type': 'object', 'required': ['text'], 'properties': {'mode': {'enum': ['mask', 'tag'], 'type': 'string', 'default': 'mask'}, 'text': {'type': 'string'}}}
Verlauf

Letzte Tool-Änderungen

Hinzugefügt
full_check
17. September 2026 12:43
Hinzugefügt
check_hallucination
17. September 2026 12:43
Hinzugefügt
check_safety
17. September 2026 12:43
Hinzugefügt
redact_pii
17. September 2026 12:43
Hinzugefügt
detect_pii
17. September 2026 12:43
Entdecken

Ähnliche MCP-Server

osint-terminal

com.thetempleofdoom.osint-mcp/osint-terminal

Provides keyless OSINT and reconnaissance tools for domains, DNS, IPs, breach exposure, threat intelligence, and related lookups.

AIMEAT

io.aimeat/aimeat

Provides a self-hosted agent operating system with agent work delegation, access controls, federation, hooks, SSO, security admin…

hyperion

com.thetempleofdoom.hyperion/hyperion

Acts as a paid MCP tool marketplace and utility gateway with server discovery, HTTP and JavaScript tools, research, data conversi…

Vee3

io.github.Vee3io/vee3

Manages Clerk authentication infrastructure, including users, organizations, domains, sessions, tokens, OAuth, SSO, machines, per…

BorealHost

ai.borealhost/mcp

Provides web hosting and infrastructure management, including site deployment, DNS, domains, containers, compute, backups, cachin…

Proof Holdings

holdings.proof/mcp-server

Provides domain verification, identity and delegation proofs, human approval workflows, trusted-contact challenges, and controlle…

GoCreative Agent API

io.github.ColinHughes2121/gocreative-agent-api

Offers pay-per-call LLM completions and data services for company intelligence, KYB, sanctions screening, threat intelligence, co…

Japan Public Ledgers MCP

com.mcp-revenue-empire/japan-public-ledgers

Provides agent identity, memory, audit, trust, proxy, temporary email, webhook, CAPTCHA, and alerting capabilities alongside publ…