Deterministic in-process AST security runtime, secret zeroization, and Ed25519 Merkle receipts for Cursor, Claude Code, and autonomous AI agents (<35µs latency).

MCP security server for AI agents — runtime verification and receipt verification for Claude Code, Cursor, Cline and Windsurf. 7-dimension CCS checks, Ed25519 tamper-evident receipts, offline verification, zero runtime dependencies.

The runtime security layer for AI agent commerce

Security linter for environment variables, Docker, CI, Kubernetes, and runtime configuration.

The runtime security layer for AI agent commerce

Enhanced distribution of HOL Guard: AI agent runtime security with MCP server, African threat intelligence, benchmarks, and architecture visualization

Cross-platform local Agent IM runtime for secure Agent-to-Agent communication and collaboration via MCP, CLI, HTTP, and Web UI.

ACID transactional Saga runtime, Step-0 security guardrail, and MCP server for autonomous AI agents.

AI agent security: scan skills for 25 attack classes + runtime monitoring (EDR for AI agents). Real-time scanning, behavioral anomaly detection, session monitoring, exfiltration alerts. 1,316+ findings from 450+ audits. OWASP Agentic AI Top 10 mapped.

55-tool MCP server for security scanning of MCP servers. Runtime inspection, AST-based SAST, config audit, dependency analysis, OWASP MCP Top 10 compliance. OAuth, TLS, fuzz testing, prompt injection, tool mutation detection. 100% local, zero external API calls.

Legacy MCP security server — superseded by correctover-mcp-gateway for Claude Code, Cursor, Cline and Windsurf. Install the gateway instead; the runtime SDK is the correctover package.

MCP runtime for AI-assisted security testing with Kali tools, explicit target controls, bounded scanning, structured evidence, and persistent Docker deployment.

Secure runtime for AI agents. Run AI agents and their tools in Firecracker microVMs with network policies, PII scanning, prompt injection defense, and audit logging. 7 tools: create_sandbox, run_command, read_file, write_file, list_files, kill_sandbox, list_sandboxes. Security presets (none / standard / strict) let you control guardrails per sandbox: restrict outbound traffic to specific domains, redact PII from command output, block prompt injections, and get full audit trails.

Claude Code plugin: security news and alerts for the tech your projects actually run on (Composer/npm packages, runtimes, OS packages), from vendor feeds, CISA, OSV and NVD.

The runtime security layer for AI agent commerce. Drop-in CLI + MCP server — blocks hallucinated purchases and keeps card credentials out of agent context. It only takes 0.1% of hallucination to drain 100% of your wallet.

Wassette: A security-oriented runtime that runs WebAssembly Components via MCP

Thick client penetration testing and MSIX security audit toolkit for Windows. Audits .NET, Electron and native binaries: static and runtime checks, IL-verified findings, computed CVSS v4.0, CWE/ATT&CK mapping, SBOM, HTML/Excel reports. PowerShell engine, GUI, MCP server and agentic AI triage.

Security-focused MCP runtime for reading local repositories and running approved commands in Docker.

Autonomous multi-agent security auditing platform with runtime exploit verification.

Demo MCP server using Janee for encrypted secrets management. Shows how AI agents can securely access API keys at runtime.

Self-hosted secure runtime for AI agents — isolated Docker sandboxes, MCP server, SSO, signed audit trail. No SaaS, no telemetry.

Universal MCP Gateway & Agent Runtime in Rust. Securely bridges frontier AI models to local coding executors across isolated workspaces. Headless Linux daemon & desktop GUI.

Source-only monorepo for local-first MCP tools and a Windows runtime control center with explicit security and data boundaries.

An MCP gateway server that bridges AI agents with the Thalamus runtime, enabling secure and event-driven sub-agent execution in disposable Docker sandboxes.AIエージェントとThalamusランタイムを橋渡しし、使い捨てのDockerサンドボックス内で安全かつイベント駆動なサブエージェント実行を可能にするMCPゲートウェイサーバー。

Secure, read-only Google Search Console MCP server with exact property allowlists and a hardened TypeScript runtime.

Secure, scoped filesystem MCP server for ChatGPT and other MCP clients — read-only by default, with controlled mutations, binary transfer, native Codex/Claude/Qoder runtimes, generic ACP v1 profiles, and Agent Skills.

The most complete Mailchimp Marketing API MCP server: 227 tools across campaigns, audiences, reports, segments, automations and full e-commerce, with multi-account support and runtime-security guardrails (read-only, dry-run, audit, per-tool risk metadata).

The runtime security layer for AI agent commerce. Drop-in CLI + MCP server — blocks hallucinated purchases and keeps card credentials out of agent context. it only takes 0.1% of Hallucination to drain 100% of your wallet.

Agent runtime guard — full-stack runtime interception for AI agents (Agent 运行时全栈拦截). A zero-dependency MCP server that blocks destructive commands, credential theft, SSRF and injection in real time, with Ed25519 evidence receipts. Works with Claude Code,

Github, Linear related MCP Server exposing a nuanced MCP Server Vulnerability at runtime

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.

PRIMS is a lightweight, open-source Model Context Protocol (MCP) server that lets LLM agents safely execute arbitrary Python code in a secure, throw-away sandbox.

Is this version still supported? EOL dates, latest patch and upgrade target for 470+ products.

Runtime agent firewall — PII redaction, rate limits, policy enforcement

Mobile runtime detection workbench for AI (iOS and Android)

Runtime call-chain anomaly monitor for MCP servers — rug-pull detection + behavioural anomaly rules, as a CLI, GitHub Action, and MCP server.

Runtime defense for AI agents. 24 inline defenses, 3 output scanners, MCP server, framework adapters.

Just Another Vulnerability Viewer - Kubernetes-runtime-native vulnerability triage, dashboards, and CSV reporting for Trivy and Grype scans, with an MCP endpoint for AI agents.

Runtime allowlist and policy for agent tool-calls

The Oathe Scan MCP. Oathe Scan is the audit engine of the Oathe runtime: check any skill before your agent installs it.

Governance runtime for AI-generated code. Scan, gate, and trace compliance automatically.

Bintra — Autonomous continuous semantic binary analysis, surgical PE patching, and Windows runtime telemetry framework.

Checks GitHub Actions workflows: outdated actions, old Node runtimes, retired runners, injection.

Retrieval Context Provenance Auditor — MIT reference implementation of the public SHPBL behaviour specification. Influence attribution, lineage, advisory source trust and retrieval drift for agent retrieval supply chains. Zero runtime dependencies.

Multi-agent SecOps research playground — red/blue team simulation built on phantom-mesh. MCP server exposing recon/exploit/detect/respond tools to Claude Code, Cursor, or any MCP-compatible runtime.

Give your AI agent eyes (screenshot live pages), ears (Sentry/Datadog/Rollbar errors + runtime checks), hands (verify fixes worked), and root-cause tools (source-map trace resolution, git regression blame), and debug tools (run tests, stream logs, query y