GHOSBC Safety Gate

Working · 2.4 s

io.github.MisfitMEdiAhouse/ghosbc-safety-gatev1.5.0

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

Security

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

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

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

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.

card_urlstring, required

Public HTTPS A2A Agent Card URL, normally /.well-known/agent-card.json.

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Tools (9)

audit_a2a_agent_card

Argument	Type	Description
card_url*	string	Public HTTPS A2A Agent Card URL, normally /.well-known/agent-card.json.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "card_url"
  ],
  "properties": {
    "card_url": {
      "type": "string",
      "format": "uri",
      "description": "Public HTTPS A2A Agent Card URL, normally /.well-known/agent-card.json."
    }
  },
  "additionalProperties": false
}

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.

Argument	Type	Description
endpoint_url*	string	Public HTTPS MCP endpoint.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "endpoint_url"
  ],
  "properties": {
    "endpoint_url": {
      "type": "string",
      "format": "uri",
      "description": "Public HTTPS MCP endpoint."
    }
  },
  "additionalProperties": false
}

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.

Argument	Type	Description
store*	string	Public Shopify store domain or HTTPS URL, for example store.myshopify.com.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "store"
  ],
  "properties": {
    "store": {
      "type": "string",
      "description": "Public Shopify store domain or HTTPS URL, for example store.myshopify.com."
    }
  },
  "additionalProperties": false
}

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.

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

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.

Argument	Type	Description
payload*	any

Input schema (JSON)

{
  "type": "object",
  "required": [
    "payload"
  ],
  "properties": {
    "payload": {}
  },
  "additionalProperties": false
}

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.

Argument	Type	Description
mode	string
text*	string
capabilities	array

Input schema (JSON)

{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "mode": {
      "enum": [
        "OPEN",
        "GUARDED",
        "SEALED"
      ],
      "type": "string"
    },
    "text": {
      "type": "string"
    },
    "capabilities": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "additionalProperties": false
}

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.

Argument	Type	Description
action*	string
amount	number
target	string
currency	string
constraints	object

Input schema (JSON)

{
  "type": "object",
  "required": [
    "action"
  ],
  "properties": {
    "action": {
      "type": "string"
    },
    "amount": {
      "type": "number"
    },
    "target": {
      "type": "string"
    },
    "currency": {
      "type": "string"
    },
    "constraints": {
      "type": "object",
      "properties": {
        "currency": {
          "type": "string"
        },
        "expires_at": {
          "type": "string",
          "format": "date-time"
        },
        "max_amount": {
          "type": "number"
        },
        "allowed_actions": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "allowed_targets": {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

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.

Argument	Type	Description
name*	string
annotations	object \| null
description	string
inputSchema	object \| null

Input schema (JSON)

{
  "type": "object",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string"
    },
    "annotations": {
      "type": [
        "object",
        "null"
      ]
    },
    "description": {
      "type": "string"
    },
    "inputSchema": {
      "type": [
        "object",
        "null"
      ]
    }
  },
  "additionalProperties": false
}

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.

Argument	Type	Description
response*	any

Input schema (JSON)

{
  "type": "object",
  "required": [
    "response"
  ],
  "properties": {
    "response": {}
  },
  "additionalProperties": false
}