HOL Guard MCP server
Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
A86/100grade A
Adoption
Established
630 stars
Reviews
Write oneNobody has reviewed HOL Guard yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
HOL Guard tools (6, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
create_policywrite actionfetchget_guard_statusget_policy_creationsearchvalidate_policy
Public scan report
scanner v0.1.9 · 2026-09-19 · same rubric, same numbers if you re-run it
1 medium
- Code scan1500 source files scanned20/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Findings (1)
- mediumeval / new Function used
exec.evalhol_guard-3.0.192/dashboard/src/apps/app-catalog.ts: …key: "encoded_execution", example: "eval(atob(...)) or base64-decoded shell paylo…
Overall 86/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON
Grade history
- 2026-09-19restoreC → Ascore 86: eval / new Function used
- 2026-09-19restoreD → Cscore 60: Whole environment serialized (possible credential exfil); Network call to a raw IP address; eval / new Function used
Install directly
claude mcp add hol-guard -- uvx hol-guard
HOL Guard: common questions
- Is HOL Guard MCP server safe?
- Yes, by our scan: it is graded A (86/100). Read the HOL Guard safety report
- How do I install HOL Guard?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does HOL Guard need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is HOL Guard maintained?
- The last commit was in the last day (2026-09-19). The latest release is v3.0.192.
- What can I use instead of HOL Guard?
- Servers from other publishers that do the same job: mcpm MCP server, Agent-Native Chat MCP server and CHAP Coordinator MCP server. Compare all HOL Guard alternatives.
Alternatives to HOL Guard
Same job from other publishers: the closest match first, then the best rated.
- mcpmMCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.not reviewedGrowingB
- Agent-Native ChatMinimal chat-first app with durable threads, actions, and the app-agent loopnot reviewedEstablishedA
- CHAP CoordinatorAuditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.not reviewedEstablishedA
- haiku.ragLocal-first agentic RAG with citations - hybrid search, reranking, multimodal document retrievalnot reviewedEstablishedA
- DvalincodeDeterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.not reviewedGrowingA