# GHOSBC Safety Gate

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

- name: io.github.MisfitMEdiAhouse/ghosbc-safety-gate
- version: 1.5.0
- connection class: R0 (autonomous)
- trust: 77/100 flags: no-repository
- quality: 83/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.MisfitMEdiAhouse%2Fghosbc-safety-gate
- tools: https://api.protogrid.dev/v1/servers/io.github.MisfitMEdiAhouse%2Fghosbc-safety-gate/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "ghosbc-safety-gate": {
      "type": "http",
      "url": "https://cibcxqrqiqvzpardbdrw.supabase.co/functions/v1/ghosbc-safety-gate-mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 45
- drivers: +website +reachable +uptime-100% ~updated-68d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 83/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list carries no ttlMs, so clients re-fetch it

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: audit_a2a_agent_card (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); audit_mcp_dependency (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); screen_agent_request (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,190 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 9, about 1,190 tokens to load them all
- tool set hash: b053f02fb2e9de28f26995667f987fc5
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.MisfitMEdiAhouse/ghosbc-safety-gate.svg)](https://protogrid.dev/servers/io.github.MisfitMEdiAhouse/ghosbc-safety-gate)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://cibcxqrqiqvzpardbdrw.supabase.co/functions/v1/ghosbc-safety-gate-mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (9)

- `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 versions, skill descriptions, security declarations and registry task-verification evidence, then returns a trust/readiness score plus shareable badge metadata. It does not send a task to or execute any skill on the target agent.
- `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 new or changed tool definitions, and produces one aggregate ALLOW/REVIEW/BLOCK decision. It does not inspect server source code or authenticated/private MCP endpoints.
- `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/mcp metadata, runs initialize/tools/list, screens exposed tool definitions, and returns a readiness/risk packet. It never creates or mutates carts, checkouts, orders, payments, credentials, or store data.
- `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 charge or receive payment credentials.
- `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 flags policy-extraction language. Not a complete DLP/compliance system.
- `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 routing; use screen_consequential_action for a concrete purchase, write, deployment, deletion or other bounded action.
- `screen_consequential_action`: Use immediately before a consequential agent action such as purchase, payment, transfer, send, deploy, publish, execute, cart mutation, checkout mutation, or delete. Compares the proposed action with caller-declared allowed actions/targets, amount ceiling, currency and expiry. ALLOW only when explicit bounds fit; REVIEW when bounds are missing; BLOCK when limits are violated. Does not execute the action.
- `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 injection-like language, credential/private-context surfaces, side-effect risk and weak contracts. Advisory metadata gate, not source-code verification.
- `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 sanitized response when review is needed. Not factuality verification.