# io.github.MisfitMEdiAhouse/ghosbc-safety-gate

Agent governance with A2A/Shopify/MCP trust audits, action screening, and decision UI.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the content rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 1.5.0
- **Author:** io.github.MisfitMEdiAhouse
- **License:** Unknown
- **Endpoints:** streamable-http https://cibcxqrqiqvzpardbdrw.supabase.co/functions/v1/ghosbc-safety-gate-mcp
- **Source:** https://cibcxqrqiqvzpardbdrw.supabase.co/functions/v1/ghosbc-safety-gate
- **Endpoint health:** reachable (last checked 2026-09-26T05:30:16.875Z, 5 samples) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the content rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: clean
- Obfuscation scan: clean
- Evidence age: 9 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-26T05:30:16.875Z
- **Version scanned:** live
- **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it.

## Tools

9 declared. Observed from a live `tools/list` probe.
- `audit_a2a_agent_card` — Use before depending on an unfamiliar A2A agent. Reads only the public Agent Card and optional public registry metadata, checks declared bindings/protocol versi
- `audit_shopify_agentic_storefront` — Use to inspect a public Shopify store's AI-shopping surface before an autonomous agent trusts it. Reads only public /.well-known/ucp, /agents.md and /api/ucp/mc
- `audit_mcp_dependency` — Use for a public remote MCP server that an autonomous agent depends on. Remembers the tools/list baseline, returns only added/removed/modified tools, screens ne
- `screen_agent_request` — Use before an agent follows untrusted instructions or requests capabilities. Returns ALLOW, REVIEW, or BLOCK plus an audit digest. Best for prompt/policy routin
- `screen_mcp_tool_definition` — Use before exposing a third-party MCP tool to an autonomous agent, or after a tool definition changed. Screens name, description, schema and annotations for inj
- `screen_consequential_action` — Use immediately before a consequential agent action such as purchase, payment, transfer, send, deploy, publish, execute, cart mutation, checkout mutation, or de
- `sanitize_agent_payload` — Use before sending context to an external model, tool or agent when the payload may contain credentials or private material. Redacts common secret patterns and 
- `validate_agent_response` — Use immediately before an agent delivers a response outside its trust boundary. Flags likely credential leakage or policy-extraction content and returns a sanit
- `buy_policy_checks` — Use only when free usage is exhausted or production volume is needed. Returns Stripe checkout for 10,000 prepaid GHOSBC Safety Gate checks for $19; it does not 

## Install

**Verdict: review** — Installable, but 2 things to check first: No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
**Cautions** (coverage gaps and advisories — never blocking)
- No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"ghosbc-safety-gate\": {\n      \"type\": \"http\",\n      \"url\": \"https://cibcxqrqiqvzpardbdrw.supabase.co/functions/v1/ghosbc-safety-gate-mcp\"\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 someone else's infrastructure; read-only tool surface.
- Floor 9, ceiling 27 (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/io.github.MisfitMEdiAhouse%2Fghosbc-safety-gate
- Install plan: https://forgeregistry.com/api/v1/packages/io.github.MisfitMEdiAhouse%2Fghosbc-safety-gate/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/io.github.MisfitMEdiAhouse%2Fghosbc-safety-gate
- HTML page: https://forgeregistry.com/registry/io.github.MisfitMEdiAhouse%2Fghosbc-safety-gate
- 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.