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 10agent-security 8cli 8cognis-digital 8
MCP server Claude CodeCodexCursor +2
Check whether an AI answer is grounded in its context — deterministic, no LLM judge. Runs locally from the @pharmatools/opengate-mcp npm package.
MCP server Claude CodeCodexCursor +2
Audit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop. Runs locally from the @nugehs/aiglare npm package.
MCP server Claude CodeCodexCursor +2
Behavioral therapy for AI agents — self-diagnosis, alignment, and training via MCP. Runs locally from the holomime npm package.
MCP server Claude CodeCodexCursor +2
MCP server "aegis" as configured in wei9072/aegis. Launched with aegis-mcp.
marmar9615-cloud/agentbridge-protocol
MCP server Claude CodeCodexCursor +2
MCP server that exposes AgentBridge actions to AI agents with confirmation gates, origin pinning, and audit logging. Default stdio transport plus an opt-in Streamable HTTP transport with bearer auth. Runs locally from the @marmarlabs/agentbridge-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
AI Agent Security System - 7-layer defense against prompt injection, data exfiltration, and AI-specific attacks. Runs locally from the zugashield Python package.
MCP server Claude CodeCodexCursor +2
Security testing toolkit for MCP servers and AI agents. Runs locally from the mcp-witness Python package.
MCP server Claude CodeCodexCursor +2
Write the rules for your AI agent once, in plain English. Deterministic code checks every tool call, and a Claude Code hook blocks the ones your rules forbid. Runs locally from the warrant-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "cognis-ragshield" as configured in cognis-digital/ragshield. Runs locally from the cognis-ragshield Python package.
MCP server Claude CodeCodexCursor +2
Verifiable memory for AI agents — 0% hallucination, cited, provably forgettable, deterministic. MCP server. CPU-only, no GPU, zero dependencies. Runs locally from the verifiable-memory-mcp Python package.
MCP server Claude CodeCodexCursor +2
Geometric-Driven Development (GDD) toolkit: cognitive rooms + Shadow Agent hooks + Ghost-Read pipeline (6 routes, persona-monologue) + thetacog-iterate convergence loop (meta-rule-checker, auto-applies high-confidence rewrites, adaptive stall-softening) +. Runs locally from the thetacog-mcp npm package.
MCP server Claude CodeCodexCursor +2
AI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base. Remote server at mcp.fronesislabs.com.
ExpertVagabond/guardrails-mcp-server
MCP server Claude CodeCodexCursor +2
AI Agent Guardrails MCP server - security layer. Runs locally from the guardrails-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
Trust scoring for AI agents. Investigate, verify, and compare agent trustworthiness through MCP. Runs locally from the agentscore-mcp npm package.
MCP server Claude CodeCodexCursor +2
LLM prompt injection firewall with session tracking, explainability and multilingual detection. Runs locally from the promptwall Python package.
MCP server Claude CodeCodexCursor +2
AI assumption firewall for MCP agents — intercepts risky decisions, detects contradictions, and gates human approval via Telegram or Slack. Runs locally from the kontrol-freek-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "olivetin-mcp" as configured in vaddisrinivas/olivetin-mcp. Runs locally from the olivetin-mcp Python package.
rithvikkatpelly/MCP-Financial-Agent
MCP server Claude CodeCodexCursor +2
MCP server "econ-data-agent" as configured in rithvikkatpelly/MCP-Financial-Agent. Runs locally from the econ-data-agent Python package.
MCP server Claude CodeCodexCursor +2
Model Context Protocol (MCP) server for EthersFlow — run proposed agent actions through federated adversarial multi-model consensus before executing them. Runs locally from the @ethersflow/mcp-server npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server "otgate" as configured in alikup-ai/otgate. Runs locally from the otgate Python package.
MCP server Claude CodeCodexCursor +2
MCP server "belay-mcp" as configured in Jairogelpi/belay-mcp. Runs locally from the belay-mcp Python package.
kiyeonjeon21/trusted-agent-stack
MCP server Claude CodeCodexCursor +2
MCP server "trusted-agent-stack" as configured in kiyeonjeon21/trusted-agent-stack. Runs locally from the trusted-agent-stack Python package.
Asaad-Suliman/hardened-terminal-mcp
MCP server Claude CodeCodexCursor +2
MCP server "hardened-terminal-mcp" as configured in Asaad-Suliman/hardened-terminal-mcp. Runs locally from the hardened-terminal-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "truthgate-agent" as configured in ay7627514-dotcom/truthgate. Runs locally from the truthgate-agent Python package.