llm-security
46 servers · 2,360★ total
ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.
Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.
Composable data security plane for Model Context Protocol. Pluggable layers — collect, analyze, guard — across 50+ enterprise providers. Open architecture.
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.
Tamper-evident integrity monitor for the MCP config & server files your local AI agents load.
Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Context Protocol servers.
Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as structured NDJSON. No code changes.
Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal guarantee no individual's record can leak even if the agent is adversarial - enforcement lives in trusted code below the model, validated by a runnable attack gallery.
Security scores for 800+ MCP servers. 9 analyzers scan for prompt injection, toxic flows, and attack surface risks. Updated daily. 🛡️
Offensive MCP server auditor: detects tool poisoning, credential leaks, RCE vectors, SSRF, session hijacking, and supply chain vulnerabilities across stdio, HTTP, and SSE transports.
MCP is being adopted rapidly. Security guidance is lagging behind. This checklist gives security engineers, platform teams, and technical leaders a clear, actionable baseline for securing MCP deployments , whether you're shipping an internal tool or a customer-facing AI agent.
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.
Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial testing, and real-time threat detection.
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.
Open-source governed memory for AI agents: prompt-injection-resistant writes, purpose-bound retrieval, provenance, and tamper-evident audit.
Activation-probe security scanner for AI agent tooling. Reads a model's internal activations to detect poisoned MCP servers, skills, and packages before install.
10 intentionally malicious MCP servers that exploit protocol features to attack AI clients. For security research and defense testing.
MCP server for remote SSH operations -- persistent sessions, structured command output, SFTP file transfer, port forwarding, and secret-safe environment variable injection with automatic output redaction.
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.
Local guardrails for AI coding agents. Wraps any MCP server and blocks destructive tool calls — DROP TABLE, rm -rf, force-push, unscoped UPDATE/DELETE — before they execute. Free, open-source, runs entirely on your machine.
Policy-as-code enforcement and observability for MCP tool calls. Wraps AI agent sessions with cryptographic integrity checks, argument-level CEL policies, and a full audit trail.
Agentic security control plane for MCP and AI agent tool calls. MCP-native policy gateway with topology discovery and audit.
🛡️ Automated security scanner for MCP (Model Context Protocol) servers — 52 rules for prompt injection, credential exposure, SSRF & tool poisoning. pip install mcp-safeguard
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.
Reliability & security proxy for the Model Context Protocol (MCP). Self-healing connections, runtime tool-poisoning/shadowing defense, and NIST AI RMF + OWASP LLM Top-10 audit trails for any MCP server. Works with Claude, Cursor, Cline, Windsurf.
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.
Offensive security framework for AI agents and MCP servers.
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.
Belay is an open-source, local-first security layer for AI coding agents (Claude Code, Codex, Cursor, OpenClaw, Hermes Agent and MCP) that blocks dangerous commands, secret leaks, and prompt injection at the tool-call boundary in under 100ms — no LLM in the decision path by default, no cloud, no phone-home.
EnigmAgent — 6-layer encrypted vault for AI agents (AES-256 + ChaCha20 + Blowfish + Fernet + 3DES + RSA). P2P sync via Gun.js. Zero cloud. Part of P2PCLAW.
Sunglasses for AI agents. Protection layer + neighborhood watch.
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.
Deterministic MCP Security Architecture. FrozenNamespace as Root of Trust for Model Context Protocol tool verification
Prompt-injection defenses for Claude Code. A PreToolUse Bash hook blocks compositional credential-exfiltration shapes (secret read plus network, env dump to network, remote script to shell, reverse shells). A sanitizing MCP server wraps untrusted URLs and files in sentinels, strips invisible unicode, flags jailbreaks.
Autonomous AI agents inside a Qubes-isolated sandbox - tag-scoped Admin API access with dom0-mediated trust boundary.
Security & governance guardrails for MCP agents in Java — audit trail, agent-to-tool authorization, prompt-injection detection and rate limiting as a zero-config Spring Boot starter.
MCP server for secure AI agent authentication — lets Claude, Claude Code, and other LLM agents call APIs without exposing raw tokens or credentials to the model
Security proxy for MCP servers. Catches indirect prompt injection attempts before they reach your AI agent.
Security, cost, and health governance proxy for MCP infrastructure — YAML policy engine, OAuth 2.1/OIDC, web dashboard, mTLS, semantic shell analysis, STRIDE threat model
A Roslyn analyzer that catches prompt-injection and tool-poisoning in C# Model Context Protocol (MCP) server tool descriptions at build time. MCPGxxx diagnostics, code fixes, and a CI gate.