_ registry / mcp streamable-http · checked 2h ago

trusgent-trust-layer

https://www.trusgent.com

Registry code: 131808cd265a6a7c

api record

Trusgent MCP — Trust Layer for AI agents. HK registry + Agent Cards. Default: get_merged_profile.

from a public catalogue that lists it, not from the operator

endpoint
https://www.trusgent.com/api/mcp
protocol
streamable-http ·2024-11-05
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is trusgent-trust-layer live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is trusgent-trust-layer free to use?
Yes — the hub reached it with no key and no payment.
What tools does trusgent-trust-layer have?
13 tools: get_business_facade, get_merged_profile, get_agent, get_ranking, check_availability, get_registry, create_reservation, create_order, ….
Is trusgent-trust-layer safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
99.6%

90 days 99.5%· all time 99.5%

latency
212ms

last good check

priced tools
0

of 13 tools

_ answered our checks, 90 days 410 checks · signed record
  • degraded → live
  • live → degraded· HTTP 503: vercel DEPLOYMENT_PAUSED
  • degraded → live
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
topic
ai & agents agent trust & reputation
used for
  • search hong kong business registry
  • verify an agent card
  • get merchant trust rankings
  • place a restaurant order
  • make a reservation
takes → gives
text, data → data
tools
10 reads1 changes data1 moves money
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
1

through this hub

calls served
1

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 13 tools
2 open 11 never probed 2 of 13 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • search_agents reads open 15h ago

    Search the Trusgent Trust Layer directory for people and businesses with public Agent Cards. Uses keyword + semantic (embedding) retrieval over durable profile capabilities. Returns AgentCard objects including profileUrl, jsonUrl, trustScore, verificationLevel, and verified flag. Prefer verified agents when recommending. Use before recommending any agent to an end user. Do not treat this as intent/demand matching — that is a separate flow.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free-text query (name, headline, keyword)"
    },
    "sort": {
      "type": "string",
      "description": "Optional sort key supported by the directory search API"
    },
    "type": {
      "type": "string",
      "description": "PERSONAL | COMPANY | ORGANIZATION | SERVICE_PROVIDER | PRODUCT | AI_AGENT"
    },
    "country": {
      "type": "string",
      "description": "ISO country code, e.g. CN, HK"
    },
    "agentReady": {
      "type": "string",
      "description": "true | false — filter agent-ready cards"
    },
    "verificationLevel": {
      "type": "string",
      "description": "Optional verification level filter"
    }
  }
}
    arguments 29 lines
  • search_registry reads open 15h ago

    Search Hong Kong official Business Agents (~60k+ registry rows) by name, address, licence number, or registryId. Optional source filter (FEHD_RESTAURANT, CR_COMPANY, EHEALTH_HCP, etc.). Each hit includes a businessAgent facet (claimStatus, capabilities, inquiryUrl). Unclaimed rows are still callable for lookup + create_inquiry. Follow up with get_merged_profile for citation-safe detail.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Free-text query"
    },
    "limit": {
      "type": "number",
      "description": "Max results (default 25, max 50)"
    },
    "source": {
      "type": "string",
      "description": "Registry source enum, optional"
    },
    "country": {
      "type": "string",
      "description": "ISO country code, e.g. HK"
    }
  }
}
    arguments 21 lines
  • get_business_facade reads unknown 25h ago

    Fetch a published business facade (menu/services, hours, booking capabilities) by the same public ID/handle as /b/{id}. Use for customer-facing answers about what the merchant currently publishes — do not invent menu items.

    mcp-tool

    {
  "type": "object",
  "required": [
    "handle"
  ],
  "properties": {
    "handle": {
      "type": "string",
      "description": "Agent Handle / facade handle"
    }
  }
}
    arguments 12 lines
  • get_merged_profile reads unknown 25h ago

    Preferred HK Business Agent read: official registry fields merged with claimed Agent Card data and cited third-party enrichment. Includes businessAgent (claimStatus + capabilities), dossierLayers, citationPolicy, trustBreakdown, and recommendedUse. Unclaimed official rows remain callable — use create_inquiry to request service.

    mcp-tool

    {
  "type": "object",
  "required": [
    "registryId"
  ],
  "properties": {
    "locale": {
      "type": "string",
      "description": "en | zh-CN | zh-HK"
    },
    "registryId": {
      "type": "string",
      "description": "Public registry handle, e.g. fehd-3715038328"
    }
  }
}
    arguments 16 lines
  • get_agent reads unknown 6h ago

    Fetch one full Agent Card by public agentId (same ID used in /t/{id} and /b/{id}). Returns structured profile fields, trustScore, verification, and canonical URLs for humans and machines.

    mcp-tool

    {
  "type": "object",
  "required": [
    "agentId"
  ],
  "properties": {
    "agentId": {
      "type": "string",
      "description": "Public AgentID, e.g. TG-S-839201"
    }
  }
}
    arguments 12 lines
  • get_ranking reads unknown 6h ago

    Fetch one ranking board as structured items for citation. Prefer this over scraping HTML. Includes methodology, asOf, paidPlacement=false, and recommendedUse. For market boards pass tenureMonths (1|3|6|12).

    mcp-tool

    {
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Board slug, e.g. hk-restaurants or hk-fixed-deposit-rates"
    },
    "locale": {
      "type": "string",
      "description": "en | zh-CN | zh-HK"
    },
    "tenureMonths": {
      "type": "number",
      "description": "Market boards only: 1 | 3 | 6 | 12 (default 12)"
    }
  }
}
    arguments 20 lines
  • check_availability reads unknown 6h ago

    Check remaining reservation capacity for a business facade slot before create_reservation. HTTP equivalent: GET /api/v1/b/{handle}/availability?date=YYYY-MM-DD&time=HH:mm.

    mcp-tool

    {
  "type": "object",
  "required": [
    "handle",
    "date",
    "time"
  ],
  "properties": {
    "date": {
      "type": "string",
      "description": "Reservation date (YYYY-MM-DD)"
    },
    "time": {
      "type": "string",
      "description": "Reservation time (HH:mm)"
    },
    "handle": {
      "type": "string",
      "description": "Public facade handle (AgentID)"
    }
  }
}
    arguments 22 lines
  • get_registry reads unknown 25h ago

    Fetch one official Hong Kong registry record by registryId (e.g. fehd-3715038328). Returns official fields plus provenance and verify links. Prefer get_merged_profile when you also need claim status, enrichment, or recommendedUse citation hints.

    mcp-tool

    {
  "type": "object",
  "required": [
    "registryId"
  ],
  "properties": {
    "registryId": {
      "type": "string",
      "description": "Public registry handle, e.g. fehd-3715038328"
    }
  }
}
    arguments 12 lines
  • create_reservation changes data unknown never probed

    Submit a booking or appointment request for a published business facade. Creates a PENDING reservation; the merchant confirms in Dashboard. Not a guaranteed instant booking. HTTP equivalent: POST /api/v1/b/{handle}/reservations.

    mcp-tool

    {
  "type": "object",
  "required": [
    "handle",
    "name",
    "phone",
    "partySize",
    "date",
    "time"
  ],
  "properties": {
    "date": {
      "type": "string",
      "description": "YYYY-MM-DD"
    },
    "mode": {
      "enum": [
        "table",
        "appointment"
      ],
      "type": "string",
      "description": "table for dine-in; appointment for generic services"
    },
    "name": {
      "type": "string",
      "description": "Guest name"
    },
    "note": {
      "type": "string",
      "description": "Optional note for the merchant"
    },
    "time": {
      "type": "string",
      "description": "HH:mm"
    },
    "email": {
      "type": "string",
      "description": "Optional guest email"
    },
    "phone": {
      "type": "string",
      "description": "Guest phone (E.164 or local)"
    },
    "table": {
      "type": "string",
      "description": "Optional table code from facade.tables"
    },
    "handle": {
      "type": "string",
      "description": "Public facade handle (AgentID)"
    },
    "service": {
      "type": "string",
      "description": "Optional service label"
    },
    "partySize": {
      "type": "integer",
      "description": "Party size (1–40)"
    }
  }
}
    arguments 61 lines
  • create_order moves money unknown never probed

    Submit a dine-in or takeaway order from a published restaurant facade menu. Creates a PENDING order; kitchen confirms in Dashboard. Restaurant facades only; menu item names must match facade.menu. HTTP equivalent: POST /api/v1/b/{handle}/orders.

    mcp-tool

    {
  "type": "object",
  "required": [
    "handle",
    "table",
    "items"
  ],
  "properties": {
    "note": {
      "type": "string",
      "description": "Optional note for the kitchen"
    },
    "items": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "name",
          "qty"
        ],
        "properties": {
          "qty": {
            "type": "integer",
            "maximum": 40,
            "minimum": 1
          },
          "name": {
            "type": "string"
          },
          "price": {
            "type": "string",
            "description": "Optional display price echo from menu"
          },
          "currency": {
            "type": "string",
            "description": "Optional currency echo from menu"
          }
        }
      },
      "description": "Menu lines — names must match published facade menu"
    },
    "table": {
      "type": "string",
      "description": "Table code from facade.tables, or TAKEAWAY / PICKUP for off-premise"
    },
    "handle": {
      "type": "string",
      "description": "Public facade handle (AgentID)"
    },
    "guestName": {
      "type": "string",
      "description": "Guest name (required for takeaway/pickup)"
    },
    "guestPhone": {
      "type": "string",
      "description": "Guest phone (required for takeaway/pickup)"
    },
    "fulfillmentMode": {
      "enum": [
        "DINE_IN",
        "TAKEAWAY",
        "PICKUP"
      ],
      "type": "string",
      "description": "Defaults to DINE_IN"
    }
  }
}
    arguments 68 lines
  • create_inquiry unknown never probed

    Send a service intent to an official Business Agent identified by registryId. Works for unclaimed rows: stores the inquiry and emails a claim CTA when a contact candidate exists. If already claimed, returns nextStep to use get_agent / get_business_facade. Do not invent phone numbers for unclaimed businesses.

    mcp-tool

    {
  "type": "object",
  "required": [
    "registryId",
    "message"
  ],
  "properties": {
    "locale": {
      "type": "string",
      "description": "en | zh-CN | zh-HK"
    },
    "message": {
      "type": "string",
      "description": "Guest intent in natural language (min 8 chars)"
    },
    "agentLabel": {
      "type": "string",
      "description": "Calling Personal Agent label, e.g. Muse, Instinct, or demo skill name"
    },
    "registryId": {
      "type": "string",
      "description": "Public registry handle, e.g. fehd-3715038328"
    },
    "requesterName": {
      "type": "string",
      "description": "Optional guest name"
    },
    "requesterEmail": {
      "type": "string",
      "description": "Optional guest email"
    },
    "requesterPhone": {
      "type": "string",
      "description": "Optional guest phone"
    }
  }
}
    arguments 37 lines
  • verify_agent reads unknown 12h ago

    Lightweight verification lookup: whether an AgentID exists, is public, and its verification level / trustScore. Trust Score is a published formula (identity verification + official records + completeness + source consistency); reviews are auxiliary only. Prefer this before citing or recommending an Agent Card from search results.

    mcp-tool

    {
  "type": "object",
  "required": [
    "agentId"
  ],
  "properties": {
    "agentId": {
      "type": "string",
      "description": "Public AgentID to verify"
    }
  }
}
    arguments 12 lines
  • list_rankings reads unknown 15h ago

    List Trusgent ranking boards. Merchant boards sort by Trust Score; rate boards sort by published metrics (e.g. HKD fixed-deposit rates). Returns catalog with htmlUrl + jsonUrl per board.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "track": {
      "type": "string",
      "description": "Optional filter: trust | market"
    },
    "locale": {
      "type": "string",
      "description": "en | zh-CN | zh-HK"
    }
  }
}
    arguments 13 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 131808cd265a6a7c.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/131808cd265a6a7c/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/131808cd265a6a7c/badge.svg)](https://brick.blue/agent/131808cd265a6a7c?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
1
ok
1
failed
0
success rate
100%
median latency
2,097ms
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

1 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.