# Vizier Guard (pypi · vizier-guard)

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

- Trust score: 72/100 (medium)
- Change this week: +19
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- pypi · `vizier-guard`: 72/100 (this document), [markdown](https://verifymcp.io/servers/vassiliylakhonin-vizier-guard/vizier-guard.md), [page](https://verifymcp.io/servers/vassiliylakhonin-vizier-guard/vizier-guard)

## Channel facts

- Registry: `pypi`
- Package: `vizier-guard`
- Version: `0.3.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 7 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 417 tokens (~139/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the Vizier Guard MCP server?

Vizier Guard runs locally as a PyPI package, launched with uvx vizier-guard. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add vassiliylakhonin-vizier-guard -- uvx vizier-guard
```

### Cursor

```json
{
  "mcpServers": {
    "vassiliylakhonin-vizier-guard": {
      "command": "uvx",
      "args": [
        "vizier-guard"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "vassiliylakhonin-vizier-guard": {
      "command": "uvx",
      "args": [
        "vizier-guard"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add vassiliylakhonin-vizier-guard -- uvx vizier-guard
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "vassiliylakhonin-vizier-guard": {
      "type": "local",
      "command": [
        "uvx",
        "vizier-guard"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add vassiliylakhonin-vizier-guard --command uvx --arg vizier-guard
```

### Hermes

```yaml
mcp_servers:
  vassiliylakhonin-vizier-guard:
    command: "uvx"
    args: ["vizier-guard"]
```

### Netclaw

```json
{
  "McpServers": {
    "vassiliylakhonin-vizier-guard": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "vizier-guard"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add vassiliylakhonin-vizier-guard -t stdio -c uvx -a vizier-guard
```

### Other

```json
{
  "mcpServers": {
    "vassiliylakhonin-vizier-guard": {
      "command": "uvx",
      "args": [
        "vizier-guard"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 72, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-09-18 (score 68, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-16 (score 53, 0)

- [functional improvement] Security disclosure: fail → pass

### 2026-09-15 (score 53, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-14 (score 68, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-13 (score 53, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-12 (score 68)

First indexed and scored.

## MCP tools (3)

### `vizier_screen_action` (~177 tokens)

Screen and authorize a proposed AI agent action before execution. Evaluates deterministic policy constraints, DLP leakage, loop prevention, and returns an ALLOW / REVIEW / BLOCK decision with an auditable cryptographic receipt.

Input parameters:

- `action_type` (string, required): Category of action: 'tool_call', 'shell_command', 'payment', 'database_write', 'external_api', 'file_modification', or 'mcp_proxy'.
- `agent_id` (string): Identifier of the agent requesting action.
- `parameters` (object): Arguments or payload of the proposed action.
- `principal_id` (string): Identifier of the human operator or principal.
- `target` (string, required): Exact target resource URI or identifier (e.g. 'mcp://github/create_issue', 'stripe://charges', 'bash://rm', 'https://api.example.com').

### `vizier_verify_receipt` (~96 tokens)

Verify a cryptographic receipt or audit proof issued by Vizier. Validates token structure, expiration, and exact request/action hash binding.

Input parameters:

- `expected_action_type` (string): Optional expected action type to verify against the receipt.
- `expected_target` (string): Optional expected target URI to verify against the receipt.
- `receipt` (string, required): The receipt token string (JWS compact or receipt JSON) issued by Vizier.

### `vizier_check_policy` (~63 tokens)

Check content or parameters against security guardrails (DLP credential/PII leaks, sanctions screening, or circuit breaker loop limits).

Input parameters:

- `category` (string, required): The policy check category.
- `content` (required): Text string, parameters object, or entity name to screen.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/vassiliylakhonin-vizier-guard/vizier-guard#diagnostics

## Score history

- 2026-09-20: 72
- 2026-09-19: 68
- 2026-09-18: 68
- 2026-09-17: 53
- 2026-09-16: 53
- 2026-09-15: 53
- 2026-09-14: 68
- 2026-09-13: 53
- 2026-09-12: 68

## Common questions

### What is the Vizier Guard MCP server?

Vizier Guard is an MCP server listed in the public MCP registry as io.github.vassiliylakhonin/vizier-guard. Deterministic authorization and security guard for AI agent actions with signed receipts. This page covers its PyPI package (vizier-guard).

### Is the Vizier Guard MCP server safe to use?

Vizier Guard scores 72 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Vizier Guard MCP server expose?

Vizier Guard exposes 3 tools: vizier_screen_action, vizier_verify_receipt, vizier_check_policy. Their descriptions and schemas cost roughly 336 tokens of context every time the server is loaded.

### Is the Vizier Guard MCP server still maintained?

Vizier Guard is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Vizier Guard MCP server under?

Vizier Guard declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/vizier-guard/
- Socket report: https://socket.dev/pypi/package/vizier-guard
- Repository: https://github.com/vassiliylakhonin/vizier
- Website: https://vizier.vassiliy-lakhonin.workers.dev/
- Changelog RSS feed: https://verifymcp.io/servers/vassiliylakhonin-vizier-guard/vizier-guard.xml
- Changelog JSON feed: https://verifymcp.io/servers/vassiliylakhonin-vizier-guard/vizier-guard.json
- HTML version of this page: https://verifymcp.io/servers/vassiliylakhonin-vizier-guard/vizier-guard