Безопасность

Работа с зависимостями проекта: поиск известных уязвимостей, оценка состояния пакетов, планирование обновлений и сохранение решений.

Проверка зависимостей AI-инструментов на известные уязвимости, анализ затронутых компонентов и создание перечня ПО в CycloneDX или SPDX.

Идентификация агентов и делегирование прав: выпуск паспортов, проверка цепочек полномочий и подписанные записи о допуске и результате.

Набор инструментов для криптосервисов: обмен токенов, условные ордера, NFT, мосты между сетями и сведения о рынке.

Cryptographic provenance, bilateral blind reputation scoring, and tamper-evident logging for AI agent interactions. 7 interlocking trust protocols (CoC, ARP, ASA, AJP, ALP, AMP, CWEP) available in Python (pip) and TypeScript (npm). 663 tests. Bitcoin-anchored provenance chains, anti-Goodhart reputation scoring…

Security & trust layer for AI agents. Scan an MCP server or skill before you install it ( scan_mcp_plugin , scan_skill ) — flags exfiltration, prompt-injection sinks, dangerous capabilities, install hooks and obfuscation → PROCEED/CAUTION/BLOCK. Plus vet_endpoint (endpoint safety verdict before an agent calls or pays…

Local-first agent memory: a plain-Markdown Obsidian vault is the source of truth, with a rebuildable DuckDB index for hybrid BM25 + vector + graph recall. Non-lossy capture with secret redaction; works across Claude Code, Codex, Cursor, and any MCP host

Crypto transaction tools for AI agents. 28 MCP tools covering swaps (Uniswap V3, Curve), yield (Aave V3, Compound V3, any ERC-4626 vault), transfers, and agent-to-agent collaboration (jobs, escrow, reputation, atomic payments, P&L). Turnkey MPC wallets + Safe Smart Accounts on Ethereum / Base / Arbitrum / Polygon.…

Query the AgentForge Trust Score (0-100 across five dimensions: security, code health, behavioral audit, community trust, EU compliance) for any MCP server before connecting. Exposes check_trust , evaluate_policy , list_trusted , and recommend tools. 3,600+ servers audited, free public API

Trust verification and security scanning for AI agents. Checks security posture of third-party MCP servers and tools with signed attestations (Ed25519/JWS) before interaction

Turns your task manager into agent memory: hybrid (dense + sparse + keyword, RRF) retrieval over TickTick or an Obsidian vault via a six-method adapter contract. MCP server + CLI, no vector DB to build or maintain. npm i -g @reneza/ats-cli

Agent OS MCP server for AI agent governance with policy enforcement, code safety verification, multi-model hallucination detection, and immutable audit trails

Action logs for AI agents. Records every agent action in a SHA-256 hash chain, making an audit trail. Install via

Trust intelligence for AI agents — identity stamps, reputation scoring (0-100), registry, forensic audit trails, and A2A passports via x402 micropayments

Identity and credential governance broker for MCP servers. Issues scoped, short-lived credentials per agent to stop credential inheritance. Audit log, human approval gates, AIMS-aligned

Permission control plane for AI agents. MCP proxy that enforces least-privilege YAML policies on every tool call, classifies sensitive data (PII/PHI), detects dangerous skill chains, and generates compliance audit trails. Supports stdio and HTTP proxy modes

Runtime policy enforcement for AI agents - prevents accidental damage to your systems, unauthorized agent access and automates backup-before-write for any touched files

Security-focused MCP server that provides safety guidelines and content analysis for AI agents

Verifiable oracle MCP server : Platon VRF ( get_random ), Chronos VDF ( compute_vdf / verify_vdf ), LUMEN reputation ( get_reputation_scores ) as agent tools. Pay-per-call over AIMarket Hub; every result independently verifiable. stdio · Python · Glama

EU AI Act compliance scanner for Python AI agents. Scans, analyzes, and remediates LangChain/CrewAI/AutoGen/OpenAI code across 6 articles with 10 tools including prompt injection detection, risk classification, and trust layer integration. The only MCP compliance server that generates fix code, not just findings

8 bundled intelligence endpoints (security, company, threat, compliance, sales, sports, property, health) via x402 micropayments on Base

Anonymize PII and redact text for GDPR across Czech and 35+ languages. Real NLP via ÚFAL/LINDAT (MasKIT + NameTag NER, not just regex), 80+ PII patterns, plus morphology, translation, and spellcheck. Czech-first, non-commercial

Memory Vault: 49 MCP tools with persistent agent memory (store/recall/search), plus 45 utility tools (QR codes, crypto prices, weather, DNS, geolocation, passwords, UUIDs, text, finance, code). Free tier + $2.99/mo Pro. or . Hosted at api.gadgethumans.com/mcp

APKTool MCP Server is a MCP server for the Apk Tool to provide automation in reverse engineering of Android APKs