Moatlight

com.moatlight由 moatlight.com 发布官方发布者v1.1.1更新于 Nov 7, 2026

Measure AI search visibility: start reports, read results and the ranked plan.

已验证Streamable HTTP可网页运行数据与分析商业与电商

概览

AI 生成的概览

Moatlight 衡量 ChatGPT 与 Google AI Overview 是否会提及某个企业,让助手发起可见度报告、读取结果并获取排序后的改进建议。

可以做什么
  • 无需登录即可读取产品说明、价格、常见问题与示例报告
  • 为某个网站创建报告草稿并发起分析任务
  • 列出、读取及批量读取报告,含阶段、进度、可见度数据与被提及的竞争品牌
  • 获取已完成报告的排序行动建议及每个买家问题的胜出者
  • 扫描网站的 agent 就绪度并读取评分、等级与排序修复项
适用场景
当用户想了解自己的企业在 AI 回答中的可见度、与竞争品牌对比,或需要具体改进措施时使用。公开工具也可让助手在注册前回答产品与价格相关问题。
运行要求
远程 HTTP 端点 moatlight.com,无需 API 密钥。报告类工具需用户在浏览器中通过 OAuth 登录,涉及 account:read、reports:read、reports:scan 等权限范围。agent 就绪度工具需付费的 Early Access 通行证,由本人在浏览器中购买。
安装前请注意
报告类工具会操作用户账户:为另一个网站创建报告会删除该用户旧网站未完成的草稿,请先确认。免费方案仅允许一个网站、每 30 天一份报告。agent 就绪度需付费通行证,付款在浏览器中完成。只读 URL 模式并不限制登录权限,若只想只读,应仅批准读取类权限范围。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Moatlight,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/com.moatlight%2Fmcp/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": {
    "moatlight": {
      "type": "http",
      "url": "https://moatlight.com/mcp"
    }
  }
}

README

Moatlight agent kit

Skills and MCP settings for using Moatlight from an AI agent.

Connect the MCP server

One URL, no API key. The client opens the OAuth login in a browser the first time a tool needs your account. Add ?readonly=true to the URL to list only the read tools on that connection (it does not change what the login allows; approve only the read scopes if you want that).

Claude Code:claude mcp add --transport http moatlight https://moatlight.com/mcp
Claude Code plugin (MCP, skills and the docs server together):claude plugin marketplace add Moatlight/moatlight-agent-kitclaude plugin install moatlight@moatlight
Codex:codex mcp add moatlight --url https://moatlight.com/mcp
Cursor:cursor://anysphere.cursor-deeplink/mcp/install?name=moatlight&config=eyJ1cmwiOiJodHRwczovL21vYXRsaWdodC5jb20vbWNwIn0%3D
Any other client (VS Code, Windsurf, Claude Desktop):{  "mcpServers": {    "moatlight": {      "type": "http",      "url": "https://moatlight.com/mcp"    }  }}

Install the skills only

bash
npx skills add Moatlight/moatlight-agent-kit

License: MIT for the files in this repository. Moatlight itself is a hosted service.

来源:README.md,提交 dc55d81

工具

13

get_product

What Moatlight does and when to use it

Facts about the product: what it does, who it is for, what it does not do, and how an agent can use it. No login. No login needed.

输入参数fields

get_pricing

Plans and prices

The free plan and the one-time Early Access pass: price, what each includes, refund window. Payment needs a person in a browser. No login. No login needed.

输入参数fields

list_faq

Frequently asked questions

Every FAQ question and answer from the home page, paged. No login. No login needed.

输入参数limitcursor

get_sample_report

A finished sample report on made-up data

Shows the shape of a real report (visibility numbers, rivals, ranked plan) for a fictional coffee roaster. Made-up data, no login. No login needed.

输入参数fields

get_account

The signed-in user, plan and limits

Returns the user's plan (free or early_access), when the pass ends, what the plan allows, and how to upgrade. Needs login with scope account:read.

输入参数fields

list_reports

List the user's reports

The user's reports, newest first, paged with a cursor. Each has its stage (analyzing, needs_confirmation, running, finished, failed). Needs login with scope reports:read.

输入参数limitcursor

create_report

Start a report for a website

Creates a report draft for a website and starts reading it. Free plan: one website, one report every 30 days. A new draft for a different website deletes the user's unfinished draft for the old one, so ask the user first. Returns 202 Accepted with the report, a job object and a Location header: poll that URL (GET /api/v1/reports/{reportId}) every few seconds until stage is needs_confirmation, then call the start endpoint. Send an Idempotency-Key header so a retry cannot start a second report. Needs login with scope reports:write.

输入参数countrywebsite必填language

batch_get_reports

Read up to 25 reports in one request

Batch read: send a list of report ids and get each report (or its error) in one answer, instead of one call per report. Each result has its own status, so one unknown id does not fail the rest. Read-only. Needs login with scope reports:read.

输入参数report_ids必填

get_report

Read one report: stage, setup to confirm, or results

While stage is needs_confirmation it returns the business profile and the proposed buyer questions. While running it returns progress. When finished it returns visibility numbers, the brands AI named, and a count of lost questions. Needs login with scope reports:read.

输入参数fieldsreportId必填

start_report

Confirm the setup and run the report

Accepts the proposed business profile and buyer questions (optionally a chosen subset of 3 to 6 question ids) and starts asking the AI engines the account includes (listed in limits.engines on GET /api/v1/me). Takes about two minutes: answers 202 Accepted with a Location header to poll until stage is finished. Safe to repeat; send an Idempotency-Key header to make a retry return the first answer. Needs login with scope reports:write.

输入参数reportId必填question_ids

get_report_actions

The ranked plan of changes and the questions you lost

For a finished report: up to three ranked moves (reason, exact edit, page, effort) and, for each buyer question AI answered with a rival, who won and why. Needs login with scope reports:read.

输入参数fieldsreportId必填

get_agent_readiness

Stored agent readiness scan (Early Access pass)

Score, grade, layer breakdown and ranked fixes from the newest scan of the report's website. Needs the Early Access pass; otherwise 402 with a link a person can open to buy it. Needs login with scope agent-readiness:read.

输入参数fieldsreportId必填

scan_agent_readiness

Run an agent readiness scan (Early Access pass)

Runs, or reuses a result under 24 hours old, for the report's website. Set force to true to scan again after fixing something. Rate limited. Needs login with scope agent-readiness:scan.

输入参数forcereportId必填

版本历史

3
  1. v1.1.1最新Nov 7, 2026
  2. v1.1.0Nov 6, 2026
  3. v1.0.0Nov 5, 2026

评分

已满足适用检查项的 100%

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