Vizier Guard MCP server

by vassiliylakhonin·io.github.vassiliylakhonin/vizier-guard·v0.3.2

Deterministic authorization and security guard for AI agent actions with signed receipts.

A89/100grade A

What users say

No reviews yet

Safety scan

A89/100

Adoption

Growing

0 stars220 downloads/wk

Reviews

Nobody has reviewed Vizier Guard yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

No tool declarations could be read from the package source. They show once the server is installed.

scanner v0.1.5 · 2026-09-19 · same rubric, same numbers if you re-run it

no findings

Code scan19 source files scanned25/25
–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 5 days ago15/15
Maintainer identityregistry namespace matches repository owner6/10

Overall 89/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

claude mcp add vizier-guard -- uvx vizier-guard

Is Vizier Guard MCP server safe?: Yes, by our scan: it is graded A (89/100). Read the Vizier Guard safety report
How do I install Vizier Guard?: It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Vizier Guard need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Vizier Guard maintained?: The last commit was 5 days ago (2026-09-15). The latest release is v0.3.2.
What can I use instead of Vizier Guard?: Servers from other publishers that do the same job: HOL Guard MCP server, Protect MCP server and SkillTotal MCP server. Compare all Vizier Guard alternatives.

Same job from other publishers: the closest match first, then the best rated.

HOL Guard
Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
not reviewed
Established
A
Protect
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
not reviewed
Growing
C
SkillTotal
Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.
not reviewed
Growing
B
mcpm
MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.
not reviewed
Growing
B
MCP
Authorize consequential AI agent actions before execution
not reviewed
Established
A