- Conduid
- Marketplace
- #llm-safety
MCP servers tagged llm-safety
15 live MCP servers tagged "llm-safety", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with llm-safety.
Execution State Preflight
Move both the checklist and the verdict outside the model. Slot-based preconditions for irreversible tool calls — execution reads a verdict record, never a conditional.
Safety Training
DPO/SafeDPO/OPAD training + eval for teaching tool-using LLMs to refuse falsely-benign MCP exploits
Piie
a privacy layer for your ai applications, prevent data leakage
Guardrail
Scan AI-generated code for security, performance, and code quality issues before they ship
Agent Airlock
Open-source security firewall for AI agents — validates tool calls, strips ghost arguments, enforces type safety, PII masking, RBAC, cost tracking & sandbox isolation. Works with…
Claude Code Invoice Guard
Deterministic guardrail (refuse, don't guess) for an LLM agent on a VAT-critical invoice workflow: skill + subagent + MCP server + PreToolUse hook. Portfolio/demo plugin.
Orchestrion
Deterministic multi-LLM orchestration with grounded, verified answers, an editable guardrail gate, and a live process dashboard.
Coach Kernel
Deterministic safety kernel for AI-agent training plans, with MCP data boundaries, Claude Agent SDK integration, replay evals, and fuzzing.
AI Security Red Team Testing Guide 2026
AI Security: Red Team Testing Guide 2026
Guardrailed AI Prospector
Automate sales prospecting with guarded AI agents for lead research, email drafting, scoring, and outreach workflows
Valta MCP
Financial guardrails for AI agents — pre-call spend gates and a cryptographically hash-chained audit trail. Stops an agent before it overspends, not after.
Sqlgate
A deterministic, fail-closed write gate for LLM-generated SQL, exposed over MCP. The model can't talk its way past it.
Agentshield LLM Safety Engine
Local-first LLM safety evaluation engine for red-teaming RAG and agentic assistants with LangGraph, MCP, human review, and regression testing.
Campus Claws
Policy-gated data excavation for AI agents on Amazon Bedrock AgentCore. Cedar + Bedrock Guardrails enforce cost limits, PII protection, and read-only access across Athena, OpenSea…
Claude Code Fact Verification Hook
Claude Code hooks to fix stale factual answers in Opus 4.7 and force verification before unsupported assertions