Trusgent MCP

io.github.Trusgent由 GitHub 账号 Trusgent 发布v1.1.0更新于 Oct 25, 2026

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

已验证Streamable HTTP可网页运行位置与生活数据与分析商业与电商

概览

AI 生成的概览

远程 MCP 服务器，让助手查询经过验证的 Agent Card、香港官方注册记录、可安全引用的合并档案，并提交商家预订与点餐请求。

可以做什么
搜索并获取个人和企业的 Agent Card，包括信任分与验证等级，并在引用前核验 AgentID。检索和读取香港官方注册记录，或获取将官方字段与认领数据、带引用的第三方补充信息合并的档案。查询商家门面的公开菜单、服务与营业时间。查询预订余量、提交待确认的预订，以及提交待确认的堂食或外卖订单。列出并获取排行榜（如商家信任榜和利率榜）的结构化条目。
适用场景
适合助手需要以可引用、带来源的数据回答香港商家或持牌机构相关问题，而不是依赖抓取猜测时；也适合在推荐某个代理或商家前核查信任与验证状态。需要向已发布商家门面提交预订或餐饮订单时同样适用。
运行要求
远程 Streamable HTTP 端点，无需本地包或运行时。公开读取无需凭据，但按 IP 限流；可在 Authorization 请求头中提供可选的 Bearer API 密钥以提高限额。需要能访问服务商端点的网络。
安装前请注意
可选 API 密钥属于机密，通过 Authorization 请求头发送。create_reservation 和 create_order 会写入数据：提交的请求在商家确认前一直处于待确认状态，不保证成功预订。查询内容和提交的详细信息会发送给第三方服务，公开读取按 IP 限流。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Trusgent MCP，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.Trusgent%2Ftrusgent-mcp/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

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

README

[Trusgent]

Trusgent MCP

Trust Layer for AI agents — verified Agent Cards, Hong Kong official registry, and citation-safe merged profiles for MCP clients.


English · 简体中文 · Developer Docs · Integration Guide · Smithery · Claude Market


🔐 Trust Layer for AI agents
✅ Verified Agent Cards
🇭🇰 60k+ HK official registry
🧩 Merged profiles with citation-safe recommendedUse
🌐 Remote endpoint: https://www.trusgent.com/api/mcp

[Smithery] [MCP Registry] [Endpoint] [GitHub Org]


Built for agents that need trustworthy business data — not scraped guesswork.

Public manifest and partner docs for Trusgent MCP — the Trust Layer remote MCP server for AI agents.

Note: The Trusgent product application (website, dashboard, registry importers) is private. This repository is intentionally public — it contains only the MCP Registry manifest, directory submission copy, and links to hosted APIs at trusgent.com. No secrets belong in this repo — see SECURITY.md.

MCP Endpoint

URLhttps://www.trusgent.com/api/mcp
TransportStreamable HTTP (JSON-RPC POST)
DiscoveryGET https://www.trusgent.com/api/mcp
AuthOptional Authorization: Bearer <api_key> — create a key. Public reads are IP rate-limited without a key.

Default Integration Flow (Hong Kong Registry)

search_registry → get_merged_profile → (if claimed) verify_agent → (optional) get_business_facade

Use get_registry only when you need raw official fields without enrichment or claim context.

Tools

  • Agent Cards: search_agents, get_agent, verify_agent, get_business_facade
  • HK official registry: search_registry, get_registry, get_merged_profile (preferred)

Documentation

Official MCP Registry

FieldValue
Product NameTrusgent MCP
Registry Nameio.github.Trusgent/trusgent-mcp
Manifestserver.json

Publish

Prerequisites: GitHub org member with permission to publish under Trusgent (io.github.Trusgent/*).

Recommended: GitHub Actions OIDC from this repo (Actions → Publish to MCP Registry → Run workflow). Local mcp-publisher login github may only grant io.github.peteyhuang/* unless the OAuth token includes org Owner scope.

bash
mcp-publisher validate server.jsonmcp-publisher login githubmcp-publisher publish server.json

Directory Submissions

PlatformCopy
Smitherysmithery-submission.md
Claude Marketclaude-market-submission.md

Client Config Example

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

Organization

All Trusgent public open-source projects: github.com/Trusgent

来源：README.md，提交 bd24d53

工具

12

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.

输入参数qsorttypecountryagentReadyverificationLevel

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.

输入参数agentId必填

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.

输入参数agentId必填

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.

输入参数handle必填

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.

输入参数date必填time必填handle必填

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.

输入参数date必填modename必填notetime必填emailphone必填tablehandle必填servicepartySize必填

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.

输入参数noteitems必填table必填handle必填guestNameguestPhonefulfillmentMode

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.

输入参数registryId必填

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.

输入参数qlimitsourcecountry

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.

输入参数localeregistryId必填

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.

输入参数tracklocale

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).

输入参数slug必填localetenureMonths

版本历史

1
  1. v1.1.0最新Sep 16, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。