# Trusgent MCP (remote · www.trusgent.com)

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

- Trust score: 86/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `www.trusgent.com`: 86/100 (this document), [markdown](https://verifymcp.io/servers/trusgent-trusgent-mcp/api-mcp.md), [page](https://verifymcp.io/servers/trusgent-trusgent-mcp/api-mcp)

## Channel facts

- Endpoint: `https://www.trusgent.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 87/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1458 tokens (~91/item across 16 items; 12 tools + 4 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the Trusgent MCP server?

Trusgent MCP is a hosted endpoint at https://www.trusgent.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http trusgent-trusgent-mcp 'https://www.trusgent.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "trusgent-trusgent-mcp": {
      "url": "https://www.trusgent.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "trusgent-trusgent-mcp": {
      "type": "http",
      "url": "https://www.trusgent.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.trusgent-trusgent-mcp]
url = "https://www.trusgent.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "trusgent-trusgent-mcp": {
      "type": "remote",
      "url": "https://www.trusgent.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add trusgent-trusgent-mcp --url 'https://www.trusgent.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  trusgent-trusgent-mcp:
    url: "https://www.trusgent.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "trusgent-trusgent-mcp": {
      "Transport": "http",
      "Url": "https://www.trusgent.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add trusgent-trusgent-mcp -t streamable-http -u 'https://www.trusgent.com/api/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-21 (score 86, 0)

- [security] Stability: 0.97 → pass

### 2026-09-20 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 85, 0)

- [functional regression] Schema quality: 1258 → 1458
- [functional] New prompt “ranking_lookup”
- [functional] New tool “get_ranking”
- [functional] New tool “list_rankings”

### 2026-09-18 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 84, 0)

- [security] Tool “search_agents” rewrote its description, which is the text the model reads
- [functional] Server version: 1.3.0 → 1.3.1
- [cosmetic] “get_business_facade” reworded the description of “handle”

### 2026-09-15 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (12)

### `search_agents` (~189 tokens)

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.

Input parameters:

- `agentReady` (string): true | false — filter agent-ready cards
- `country` (string): ISO country code, e.g. CN, HK
- `q` (string): Free-text query (name, headline, keyword)
- `sort` (string): Optional sort key supported by the directory search API
- `type` (string): PERSONAL | COMPANY | ORGANIZATION | SERVICE_PROVIDER | PRODUCT | AI_AGENT
- `verificationLevel` (string): Optional verification level filter

### `get_agent` (~75 tokens)

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.

Input parameters:

- `trusgentId` (string, required): Public AgentID, e.g. TG-S-839201

### `verify_agent` (~80 tokens)

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.

Input parameters:

- `trusgentId` (string, required): Public AgentID to verify

### `get_business_facade` (~67 tokens)

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.

Input parameters:

- `handle` (string, required): Agent Handle / facade handle

### `check_availability` (~86 tokens)

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.

Input parameters:

- `date` (string, required): Reservation date (YYYY-MM-DD)
- `handle` (string, required): Public facade handle (AgentID)
- `time` (string, required): Reservation time (HH:mm)

### `create_reservation` (~185 tokens)

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.

Input parameters:

- `date` (string, required): YYYY-MM-DD
- `email` (string): Optional guest email
- `handle` (string, required): Public facade handle (AgentID)
- `mode` (string): table for dine-in; appointment for generic services
- `name` (string, required): Guest name
- `note` (string): Optional note for the merchant
- `partySize` (integer, required): Party size (1–40)
- `phone` (string, required): Guest phone (E.164 or local)
- `service` (string): Optional service label
- `table` (string): Optional table code from facade.tables
- `time` (string, required): HH:mm

### `create_order` (~172 tokens)

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.

Input parameters:

- `fulfillmentMode` (string): Defaults to DINE_IN
- `guestName` (string): Guest name (required for takeaway/pickup)
- `guestPhone` (string): Guest phone (required for takeaway/pickup)
- `handle` (string, required): Public facade handle (AgentID)
- `items` (array, required): Menu lines — names must match published facade menu
- `note` (string): Optional note for the kitchen
- `table` (string, required): Table code from facade.tables, or TAKEAWAY / PICKUP for off-premise

### `get_registry` (~81 tokens)

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.

Input parameters:

- `registryId` (string, required): Public registry handle, e.g. fehd-3715038328

### `search_registry` (~125 tokens)

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.

Input parameters:

- `country` (string): ISO country code, e.g. HK
- `limit` (number): Max results (default 25, max 50)
- `q` (string): Free-text query
- `source` (string): Registry source enum, optional

### `get_merged_profile` (~110 tokens)

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.

Input parameters:

- `locale` (string): en | zh-CN | zh-HK
- `registryId` (string, required): Public registry handle, e.g. fehd-3715038328

### `list_rankings` (~80 tokens)

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.

Input parameters:

- `locale` (string): en | zh-CN | zh-HK
- `track` (string): Optional filter: trust | market

### `get_ranking` (~120 tokens)

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).

Input parameters:

- `locale` (string): en | zh-CN | zh-HK
- `slug` (string, required): Board slug, e.g. hk-restaurants or hk-fixed-deposit-rates
- `tenureMonths` (number): Market boards only: 1 | 3 | 6 | 12 (default 12)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/trusgent-trusgent-mcp/api-mcp#diagnostics

## Score history

- 2026-09-21: 86
- 2026-09-20: 86
- 2026-09-19: 85
- 2026-09-18: 85
- 2026-09-17: 84
- 2026-09-16: 84
- 2026-09-15: 84
- 2026-09-14: 83
- 2026-09-13: 83
- 2026-09-12: 82
- 2026-09-11: 82
- 2026-09-10: 81
- 2026-09-09: 81
- 2026-09-08: 80
- 2026-09-07: 80
- 2026-09-06: 79
- 2026-09-05: 79
- 2026-09-04: 78
- 2026-09-03: 78
- 2026-09-02: 78
- 2026-09-01: 77
- 2026-08-31: 77
- 2026-08-30: 76
- 2026-08-29: 76
- 2026-08-28: 75
- 2026-08-27: 75
- 2026-08-26: 74
- 2026-08-25: 72
- 2026-08-24: 72
- 2026-08-23: 71

## Common questions

### What is the Trusgent MCP server?

Trusgent MCP is listed in the public MCP registry as io.github.Trusgent/trusgent-mcp. Trusgent MCP, Trust Layer for AI agents. HK registry + Agent Cards. Default: get_merged_profile. This page covers its hosted endpoint (https://www.trusgent.com/api/mcp).

### Is the Trusgent MCP server safe to use?

Trusgent MCP scores 86 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Trusgent MCP server expose?

Trusgent MCP exposes 12 tools: search_agents, get_agent, verify_agent, get_business_facade, check_availability, and 7 more. Their descriptions and schemas cost roughly 1,370 tokens of context every time the server is loaded.

### Does the Trusgent MCP server require authentication?

No. We connected to Trusgent MCP without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Trusgent MCP server still maintained?

Trusgent MCP is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://www.trusgent.com/api/mcp
- Repository: https://github.com/Trusgent/trusgent-mcp
- Website: https://www.trusgent.com/en/developers
- Changelog RSS feed: https://verifymcp.io/servers/trusgent-trusgent-mcp/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/trusgent-trusgent-mcp/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/trusgent-trusgent-mcp/api-mcp