{"opensite":"0.1","url":"https://hol.org/guard","canonical":"https://hol.org/guard","site":{"name":"HOL Points Portal","web":"https://hol.org"},"kind":"product","title":"HOL Points Portal","description":"HOL, also known as Hashgraph Online, builds open standards, registries, developer infrastructure, and runtime security for AI agents. The portal hosts HOL Guard, the Universal Agentic Registry, HOL Points, HCS standards, and public developer resources.","image":{"url":"https://hol.org/guard/og/landing"},"language":"en","tags":["ai agent security","mcp server security","mcp server scanner","ai harness security","codex security","claude code security"],"feeds":[],"published_at":null,"modified_at":null,"fetched_at":"2026-10-21T17:28:53.896Z","status":"live","source":"read","cards":{"og":{"title":"HOL Guard | Control risky AI actions before they run","description":"Control risky AI actions on supported integrations, from commands and tool calls to installs and configuration changes.","url":"https://hol.org/guard","image":"https://hol.org/guard/og/landing","image:width":"1200","image:height":"630","image:alt":"HOL Guard AI agent security","type":"website"},"twitter":{"card":"summary_large_image","site":"@HashgraphOnline","creator":"@HashgraphOnline","title":"HOL Guard | Control risky AI actions before they run","description":"Control risky AI actions on supported integrations and keep a record of what happened.","image":"https://hol.org/guard/og/landing"}},"jsonld":[{"@context":"https://schema.org","@type":"SoftwareApplication","@id":"https://hol.org/guard/features#software","applicationCategory":"SecurityApplication","softwareVersion":"2.2.118","sameAs":["https://huggingface.co/datasets/HashgraphOnline/hol-plugin-security","https://hol.org/guard/security/owasp-mcp-top-10"],"description":"AI agent runtime security with surface-specific pre-action controls plus separate supply-chain inspection for packages, skills, plugins, and MCP configuration.","publisher":{"@type":"Organization","name":"HOL"},"url":"https://hol.org/guard/features","screenshot":"https://hol.org/og/guard-features-comparison.png","featureList":["Surface-specific pre-action interception","Policy routing with allow, observe, ask, and block outcomes","Local review and evidence workflows","MCP, skill, plugin, and package inspection","Layered local and team policy","Explicit stable versus alpha compatibility claims"],"offers":[{"@type":"Offer","name":"Free","price":"0","priceCurrency":"USD"},{"@type":"Offer","name":"Solo","price":"4.99","priceCurrency":"USD"},{"@type":"Offer","name":"Pro","price":"15","priceCurrency":"USD"},{"@type":"Offer","name":"Team","price":"30","priceCurrency":"USD"},{"@type":"Offer","name":"Enterprise","description":"Contact sales for pricing."}]},{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"What is HOL Guard?","acceptedAnswer":{"@type":"Answer","text":"HOL Guard is a local-first runtime security layer for AI agents. Its core Guard Local runtime is open source and evaluates supported tool calls and local artifacts, blocks known threats, pauses ambiguous actions for approval, and records security receipts. Guard Local runs on the developer machine without a cloud account. Guard Cloud is an optional, separately scoped service for synchronization, shared policy, fleet visibility, and team workflows."}},{"@type":"Question","name":"What does HOL Guard protect against?","acceptedAnswer":{"@type":"Answer","text":"HOL Guard protects supported AI-agent workflows against secret and credential exposure, destructive commands, prompt-injection-driven actions, malicious or changed packages, risky MCP configuration, and unsafe plugins, skills, hooks, and agent settings. Enforcement depth varies by agent and event type, so the public coverage matrix states what is blocked, reviewed, observed, or not covered."}},{"@type":"Question","name":"Is HOL Guard open source?","acceptedAnswer":{"@type":"Answer","text":"HOL Guard's core Guard Local runtime is open source under Apache-2.0. It can be installed, inspected, and used without a paid plan or cloud account, and normal local protection continues offline. Guard Cloud is an optional, separately scoped service for synchronized evidence, shared policy, fleet visibility, and team workflows."}},{"@type":"Question","name":"What are the best alternatives to HOL Guard?","acceptedAnswer":{"@type":"Answer","text":"The best alternative depends on the control boundary you need. Native agent approvals confirm individual actions, static scanners inspect packages and MCP configurations, sandboxes isolate processes, model guardrails filter prompts and outputs, and gateways centralize MCP or network traffic. HOL Guard is the open-source local-runtime option for cross-agent policy, pre-execution review on supported events, approvals, and local evidence."}}]}]}