Security
AI agents for threat detection, access control, vulnerability scanning, and security policy enforcement. From SIEM integrations to agent-level sandboxing and governance layers, these tools protect AI systems and the applications they power. Increasingly essential as agentic workloads expand.
Agent Payment Safety Audit Desk
Human audit service for agent payment, x402, MCP, and wallet workflow safety. Reviews route discovery, 402 handling, se…
Agent Vault
Open-source credential proxy for AI agents by Infisical. Agents call APIs without ever seeing secrets — credentials inj…
Arcade.dev
Handles agent authorization, tool calling, and governance so agents act on behalf of users. MCP runtime with Python/JS…
Clawvisor
Human-in-the-loop security gateway for AI agents. Approves, verifies, and audits every API call across Gmail, GitHub, S…
CrowdStrike Charlotte AI
Generative AI security analyst that investigates threats, provides attack summaries, and recommends remediation across…
Descope
Drag-and-drop authentication platform with visual workflow builder for auth flows, MFA, and user management.
Docker Sandboxes
Disposable, isolated container sandboxes for running untrusted agent-generated code, with filesystem and network isolat…
Ghidra MCP
Connects AI to Ghidra for AI-assisted reverse engineering — 110 tools for decompilation, function analysis, disassembly…
IDA Pro MCP
Bridges IDA Pro to LLM clients over MCP, exposing decompilation, disassembly, cross-references, type and stack edits, m…
NeMo Guardrails
Adds programmable guardrails to LLM apps — input/output moderation, jailbreak and prompt-injection detection, topic con…
Nightcrawler
Local AI pentesting agent that runs reconnaissance and vulnerability probing from your own hardware without sending sco…
NVIDIA NemoClaw
Open-source security runtime for multi-agent AI. Enforces policy-based access control, sandboxes kernel interactions, a…
OneCLI
Stores API keys in a central gateway and injects them into outbound requests at call time, so AI agents can use credent…
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…
PentAGI
Executes penetration-testing workflows with autonomous agent teams that chain reconnaissance, exploitation, and reporti…
promptfoo
Tests and red-teams LLM apps, agents and RAG pipelines from declarative config, scanning for prompt injection, jailbrea…
SafeWeave
MCP server with 8 parallel security scanners — SAST, secrets, dependencies, IaC, container, DAST, license, and posture.…
Semgrep
Scans source code with AI-assisted SAST, SCA, and secrets detection, finding 8x more true positives with 50% less noise…
Snyk
Developer security platform with AI-powered vulnerability detection, fix suggestions, and automated security testing ac…
Snyk Agent Scan
Security scanner for MCP servers and agent skills. Detects prompt injections, tool poisoning, and sensitive data risks…
Socket Security
Detects malicious and risky packages in npm, PyPI, and open-source dependencies before install using static analysis an…
Stytch
Authentication and identity platform with passwordless login, session management, and fraud detection APIs for modern a…
SWE-agent
Takes a GitHub issue and autonomously fixes it with the language model of your choice. Also runs cybersecurity/CTF task…
Tabnine
Code completion and chat assistant with self-hosted and air-gapped deployment options for teams with strict code-privac…
Warden
AI code review agent from Sentry — define review skills in Markdown, run locally before pushing or auto-trigger on ever…