# Trusgent MCP

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

- name: io.github.Trusgent/trusgent-mcp
- version: 1.1.0
- connection class: R0 (autonomous)
- trust: 94/100
- quality: 91/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.Trusgent%2Ftrusgent-mcp
- tools: https://api.protogrid.dev/v1/servers/io.github.Trusgent%2Ftrusgent-mcp/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "trusgent-mcp": {
      "type": "http",
      "url": "https://www.trusgent.com/api/mcp",
      "headers": {
        "Authorization": "Bearer ${TRUSGENT_API_KEY}"
      }
    }
  }
}
```

Placeholders to fill: `${TRUSGENT_API_KEY}`.

## Trust

- hygiene: 100
- liveness: 100
- freshness: 85
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% ~updated-58d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 91/100 (strong)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2024-11-05; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### 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: 100 (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
- pass `tools.annotations`: 12 of 12 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 2,138 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`: 2 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: 12, about 2,138 tokens to load them all
- tool set hash: fb38b6b96fdaabe6ebaec79cb28c6403
- tools last changed: 2026-10-10T13:22:56.183Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.Trusgent/trusgent-mcp.svg)](https://protogrid.dev/servers/io.github.Trusgent/trusgent-mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-10 `verify_agent` changed (inputSchema)
- 2026-10-10 `get_agent` changed (description, inputSchema)
  - before: Fetch one full Agent Card by public trusgentId (same ID used in /t/{id} and /b/{id}). Returns structured profile fields, trustScore, verification, and canonical URLs for humans and machines.
  - after: 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.

Full history: https://api.protogrid.dev/v1/servers/io.github.Trusgent%2Ftrusgent-mcp/changes

## Remotes

- https://www.trusgent.com/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (12)

- `check_availability`: 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.
- `create_order`: 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.
- `create_reservation`: 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.
- `get_agent`: 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.
- `get_business_facade`: 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.
- `get_merged_profile`: Preferred HK registry read: official registry fields merged with claimed Agent Card data and cited third-party enrichment (Google Places POC when available). Includes dossierLayers, citationPolicy, trustBreakdown, and recommendedUse so agents know what is safe to cite. Reviews are auxiliary and are not scraped from the open web.
- `get_ranking`: 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).
- `get_registry`: 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.
- `list_rankings`: 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.
- `search_agents`: 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.
- `search_registry`: Search Hong Kong official registry records (~60k+) by name, address, licence number, or registryId. Optional source filter (FEHD_RESTAURANT, EHEALTH_HCP, etc.). Returns lightweight rows with profileUrl and mergedUrl; follow up with get_merged_profile for citation-safe detail.
- `verify_agent`: 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.