151 tagged AI Safety, measured the same way as everything else here.
Browse within: ai-governance 33Guardrails 22LLM 22model-context-protocol 19ai-security 16compliance 16mcp-server 16AI-policy 11agent-orchestration 11agentic-ai 11audit 10cursor 9agent-security 8cli 8
MCP server Claude CodeCodexCursor +2
Deterministic, no-LLM MCP server that scrubs secrets from text/logs/transcripts before they enter agent context. Never leaks the value. Runs locally from the mcp-secret-scrub Python package.
MCP server Claude CodeCodexCursor +2
MCP server auditing agent skills/system prompts against 8 malicious-skill supply-chain patterns (deterministic, no-LLM). Runs locally from the mcp-skill-sec Python package.
MCP server Claude CodeCodexCursor +2
MCP server forcing evidence-gated, honestly-tiered claim reporting (FACT/INFERENCE/SPECULATION), deterministic no-LLM. Runs locally from the mcp-verify-claim Python package.
COSTRINITY/vitna-compliance-mcp
MCP server Claude CodeCodexCursor +2
Pre-action allow/deny for AI agents. 24 statutes, 13 jurisdictions: EU AI Act, GDPR, DPDP. Runs locally from the @costrinity/vitna-compliance-mcp npm package. Needs 4 environment variables to run.
MCP server Claude CodeCodexCursor +2
Security Through Absurdity - Transform attacks into hiking boot advertisements. By Claude & Jasper from HumoticaOS. Runs locally from the mcp-server-inject-bender Python package.
MCP server Claude CodeCodexCursor +2
MCP server "provena" as configured in parkseokjune/provena. Runs locally from the provena npm package.
MCP server Claude CodeCodexCursor +2
MCP Server for QWED Verification - Use QWED verification tools in Claude Desktop, VS Code, and any MCP client. Runs locally from the qwed-mcp Python package.
halvrenofviryel/phionyx-pipeline-mcp
MCP server Claude CodeCodexCursor +2
Phionyx self-governance gate for Claude Code — three-layer verification (LLM declaration → git diff truth → deterministic gate) over the agent's own 'fixed / tested / changed' claims. v0.3.0 adds opt-in evidence binding: the requiretool directive (a factual claim without same-turn evidence must bind a tool first) and…
MCP server Claude CodeCodexCursor +2
10th Man Protocol — Adversarial review MCP server for Claude Code. Spawns 3 contrarian agents to challenge proposed code changes before execution. Runs locally from the tenth-man-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "cognis-aegis" as configured in cognis-digital/aegis. Runs locally from the cognis-aegis Python package.
MCP server Claude CodeCodexCursor +2
MCP server "cognis-adversa" as configured in cognis-digital/adversa. Runs locally from the cognis-adversa Python package.
MCP server Claude CodeCodexCursor +2
MCP server "cognis-aicard" as configured in cognis-digital/aicard. Runs locally from the cognis-aicard Python package.
MCP server Claude CodeCodexCursor +2
MCP server "cognis-biascope" as configured in cognis-digital/biascope. Runs locally from the cognis-biascope Python package.
MCP server Claude CodeCodexCursor +2
MCP server "cognis-guardpost" as configured in cognis-digital/guardpost. Runs locally from the cognis-guardpost Python package.
MCP server Claude CodeCodexCursor +2
MCP server "cognis-hallumark" as configured in cognis-digital/hallumark. Runs locally from the cognis-hallumark Python package.
MCP server Claude CodeCodexCursor +2
MCP server "cognis-ledgermind" as configured in cognis-digital/ledgermind. Runs locally from the cognis-ledgermind Python package.
MCP server Claude CodeCodexCursor +2
Confidence-Consistency Evaluation for Time Series Anomaly Detection. Runs locally from the cce Python package.
MCP server Claude CodeCodexCursor +2
MCP server "agentcloud", hosted remotely at {agentcloudhost}, as configured in premhiru/agentcloud.
MCP server Claude CodeCodexCursor +2
Create sentinel objects, akin to None, NotImplemented, Ellipsis. Runs locally from the sentinel Python package.
MCP server Claude CodeCodexCursor +2
TokenSpy MCP Server — AI pitfall intelligence and trading signals for agents. Runs locally from the tokenspy-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "skillguard" as configured in epistemedeus/skillguard. Launched with epistemedeus/skillguard.
MCP server Claude CodeCodexCursor +2
MCP server and CLI for detecting, redacting, and auditing PHI before medical text is sent to AI agents. Runs locally from the phi-guard-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server and CLI for detecting, redacting, and auditing PHI before medical text is sent to AI agents. Runs locally from the phi-guard-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "agent-eval-gate" as configured in linus10x/agent-eval-gate. Runs locally from the agent-eval-gate Python package.