# GHOSBC Safety Gate

- Registry name: `io.github.MisfitMEdiAhouse/ghosbc-safety-gate` · version 1.5.0
- Categories (automatic, keyword rules): Shops & products, Commerce & marketing, Payments & accounting, Finance & markets
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): extensions, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.MisfitMEdiAhouse%2Fghosbc-safety-gate
- Server page: https://mcpstation.net/s/io.github.MisfitMEdiAhouse--ghosbc-safety-gate.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://cibcxqrqiqvzpardbdrw.supabase.co/functions/v1/ghosbc-safety-gate-mcp`

## Tools (as reported by the server, not verified)

- `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
- `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 c
- `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 authenticat
- `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\_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 veri
- `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 explic
- `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.
- `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.
- `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.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html