agent-security
39 servers · 3,206★ total
ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.
Consequence firewall for machine actions. EMILIA Gate verifies exact authority before money, code, permissions, infrastructure, or regulated state changes; the open protocol makes the evidence independently verifiable.
CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.
See what your AI agents can access. Scan MCP configs for exposed secrets, shadow APIs, and AI models. Generate AI-BOMs for compliance.
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers
Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.
Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
Security control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP. Guards a real Claude Code end to end.
Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as structured NDJSON. No code changes.
Python SDK for accurate and verifiable agent tool use. Agents verify that answers came from the right source and were not changed. Downstream agents detect 100% of errors and retry to achieve a 50% jump in answer accuracy.
Agentic SAMM - An OWASP SAMM Extension for AI-Driven Development
The ultimate OWASP MCP Top 10 security checklist and pentesting framework for Model Context Protocol (MCP), AI agents, and LLM-powered systems.
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.
Forensic auditor for local AI coding agents (Claude Code, Codex CLI, OpenClaw) and project-surface scanner for repos containing skills, plugins, and MCP manifests. Reads session logs, configs, and instruction files, detects known-bad patterns using 296 bundled rules in total.
Multi-engine security scanner for AI agents, MCP servers & plugins — 13 engines, one report.
Security scanner for Model Context Protocol (MCP) with capability graph analysis. Detects emergent attack chains across multi-server AI agent deployments that no individual tool scan can find.
Activation-probe security scanner for AI agent tooling. Reads a model's internal activations to detect poisoned MCP servers, skills, and packages before install.
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.
Discover and audit MCP servers for security vulnerabilities across Claude Code, Cursor, VS Code, and more
Runtime security proxy for MCP: lockfile enforcement, drift detection, artifact pinning, Sigstore/Ed25519 signing, CEL policy, OpenTelemetry tracing. Works with Claude Desktop, LangChain, AutoGen, CrewAI.
Security for AI agents & MCP — map how MCP servers, skills, and memory chain into exposure paths. Toxic-flow detection, cross-surface graph, drift & policy-as-code. Local-only, no telemetry.
Assay — a canary-oracle benchmark for MCP security: a frozen task set scored by a recomputable HMAC-canary oracle (structural-zero false positives), not an LLM judge. Maintained by Verosek.
Collateralized execution engine for AI agents: bond-and-slash accountability with Ed25519 identities, bounded exposure, and progressive trust tiers.
A deep, visual, source-grounded guide from LLMs and agent architectures to secure agentic AI systems.
Runtime policy enforcement and audit control plane for MCP tool execution. Deterministic, non-AI policy engine that intercepts MCP tools/call requests before execution.
Agents change faster than audits. Ancilis discovers what agents can do, classifies the data they touch, activates the right controls, and continuously proves compliance. Trust your agents in production.
Authorization, delegation, provenance, and verifiable-audit engine for AI agents. MCP adapter published.
A local proxy that wraps your MCP servers and checks each tool call against policy and live state before it runs - allow, block, or request a refresh, with a reason the agent can act on.
Agent Run Config — an open specification for declaring, packaging, securing, and sharing portable, governed AI agents. Like a Dockerfile for agents: one reviewable Agentfile for identity, tools, boundaries, policy, and OCI packaging.
Sunglasses for AI agents. Protection layer + neighborhood watch.
Verifiable agent identity for A2A and MCP. Cryptographic claims, append-only transparency log, recovery-key revocation. Apache 2.0.
Local PII and secret redaction for Python LLM apps and AI agents. Zero dependencies. Prompts, tool calls, MCP, memory, logs, and traces.
Security scanner for Model Context Protocol servers. Catch tool poisoning, prompt injection, and supply-chain attacks before your AI agent runs them.
Autonomous AI agents inside a Qubes-isolated sandbox - tag-scoped Admin API access with dom0-mediated trust boundary.
Security scanner and developer toolkit for MCP servers used by AI agents.
Runtime guardrails for AI agent MCP tools. Blocks dangerous tool calls at runtime with a default-deny policy proxy.
Description: Local-first pre-commit policy guard for AI-agent repositories. Website: https://pypi.org/project/aigenguard/