#ai-safety

MCP servers expose tools with no information about what they actually do at runtime. mcpsafetywarden sits between your agent and any MCP server, profiling tool behavior, blocking destructive calls, and running active security audits before you trust them in a workflow.

Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

Runtime policy enforcement and audit control plane for MCP tool execution. Deterministic, non-AI policy engine that intercepts MCP tools/call requests before execution.

BonkLM - LLM Security Guardrails with Interactive Setup Wizard

Cognitive Browser: The browser automation that thinks. Constitutional safety • Persona UX testing • Natural language interface • Self-healing selectors • Built for AI agents

Zero-trust governance layer for Claude Code. Policy-enforced MCP gateway with autonomy controls, middleware chain, audit log, HALT kill-switch, and prompt-injection defense.

Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-boundary leaks), mcp-ssrf-check, and a self-hosted redacting gateway.

Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,583 patterns across 117 categories and reports findings and incomplete scans. A Claude Code hook blocks secret material in tool calls and the paths and hosts your policy lists before tools run.

Deploy AI-generated web apps to your own Kubernetes cluster in seconds, over MCP. No container build on the deploy path.

EgisAI SDK

The authorization kernel for AI agents. Block, allow, or escalate agent tool calls with YAML rules — deterministic-first, LLM fallback.

Deterministic governance for Claude and MCP tool calls. Pin approved capabilities, detect drift, and refuse unsafe or unapproved actions before execution. No model in the decision path.

Runtime control, security, and governance for AI agents — decide what an agent may do at the moment it acts, revoke that authority instantly, and keep tamper-evident evidence of every decision.

Runtime constitutional governance for autonomous AI agents: six gates, 12 hard constraints, and cross-session risk composition — escalates on the trajectory, catching agents that pass every individual gate but accumulate risk across a sequence. pip install constitutional-agent

License Compliance Checker — Multi-ecosystem license + AI model scanner for EU AI Act Article 53 GPAI compliance. SBOM, SARIF, training-data risk. Apache 2.0.

AuspexAI volunteer worker for donating compute to AI research

Constraint-driven runtime for TypeScript. Declare requirements, let the runtime resolve them.

Deterministic pre-write guard for AI coding agents. Blocks an Edit/Write that references a symbol your repo doesn't have — before it lands, not after the build fails. No LLM, no API keys, ~0 tokens: the same code produces the same answer. Catches hallucinated bare calls, consts and type refs; 4 of 9 on our real-hallucination benchmark.

Per-operation approval and audit logging for secret access and git commit signing on Linux

Schema-backed contract layer for governed AI/security workflows: intent, policy decisions, approvals, execution receipts, evidence, and replayable audit traces.

Pre-action evidence revalidation for AI agents. Detect stale reasoning before agents write, send, update, or delete.

AI agent & MCP trust registry — independent, evidence-based trust scores for 1.3K+ open-source AI agents and MCP servers. Runtime-trust calibrated (MCP, dependencies, provenance drift), with side-by-side comparison and embeddable live badges. Ranked by verifiable signals, not hype.

Shield models AI safety the way humans experience safety