# enforcer-governor

GVNR (gvnr.io): stops AI agents overspending and running dangerous commands before they act.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the package rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.30.0
- **Author:** io.gvnr
- **License:** FSL-1.1-ALv2
- **npm:** enforcer-governor
- **Source:** https://github.com/instruxi-io/enforcer-governor
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

60/100 (B), scored on the package rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 9 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-26T13:02:03.598Z
- **Version scanned:** 0.30.0
- **CVEs:** none found by OSV at scan time

## Tools

6 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `gvnr_request_permission` — Ask GVNR whether an action is allowed BEFORE you run it. Call this before any shell command, file deletion, git push, deploy or publish, and before reading or w
- `gvnr_status` — Show every governed agent with its status, spend and spend rate, plus the limits in force and what has been spent today, this week and this month.
- `gvnr_recent_decisions` — List the most recent allow, deny and ask decisions from the receipt file, newest last.
- `gvnr_verify_receipts` — Check the hash chain over every recorded decision. Reports whether it is intact, or the line where a record was edited or removed.
- `gvnr_stop_agent` — Stop a governed agent immediately. Only a human can resume it, from the GVNR dashboard. Use gvnr_status for agent ids.
- `gvnr`

## Install

**Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for.
**Cautions** (coverage gaps and advisories — never blocking)
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"enforcer-governor\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"enforcer-governor\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on your machine; read-only tool surface.
- Floor 11, ceiling 29 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/enforcer-governor
- Install plan: https://forgeregistry.com/api/v1/packages/enforcer-governor/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/enforcer-governor
- HTML page: https://forgeregistry.com/registry/enforcer-governor
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.