Mcp Agent Accessibility Auditor

com.mambabuilt由 mambabuilt.com 发布v1.3.1更新于 Nov 7, 2026

Audit whether an AI agent can read a site: llms.txt, robots AI rules, structured data.

已验证STDIO仅桌面网页搜索与抓取开发者工具

概览

AI 生成的概览

审计网站能否被 AI 智能体读取，检查 llms.txt、robots 中的 AI 爬虫规则、结构化数据、渲染模式与机器可读端点。

可以做什么
  • 审计单个域名的智能体可读性，返回含 42 个字段的一行结果
  • 检查 llms.txt、llms-full.txt 与 ai.txt 是否存在且有效
  • 查看 robots.txt 中的 AI 爬虫策略，包括 Content Signal 指令
  • 检查结构化数据：JSON-LD、microdata、Open Graph 与 canonical
  • 探测 sitemap、OpenAPI、security.txt、feeds 等机器可读端点
  • 可只运行指定检查项，或为单次运行设置费用上限
适用场景
适合为 AI 爬虫与智能体流量做准备的 SEO 或增长工程师，也适合需要为客户清单做前后对比审计的代理机构。它返回的是抓取得到的事实，而非模型判断，结果稳定可复现。
运行要求
以 Node.js 包形式通过 npx 在本地以 stdio 运行。需要 Apify 账号和 APIFY_TOKEN 环境变量；工具会调用 Apify actor 并消耗 Apify 额度。
安装前请注意
运行会产生费用：按分析的域名数量计费并另收 actor 启动费，且消耗 Apify 额度，可用 max_charge_usd 设置上限。APIFY_TOKEN 密钥通过环境变量传入。提交的域名会发送到 Apify 的 actor，结果默认缓存 7 天，除非设置 skipCache。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Mcp Agent Accessibility Auditor，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。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Agent Accessibility Auditor MCP Server

[Glama score] [MCP Registry] [npm version] [npm downloads] [license] [mcpservers.org]

[Agent Accessibility Auditor MCP server]

MCP server for the Mamba Labs Agent Accessibility Auditor actor on Apify.

Can an AI agent read this site? Give it a domain and it returns one flat row of 42 fields covering five families of fact: the llms.txt family, robots AI crawler policy including the newer Content Signal directives, structured data presence and health, render mode, and machine readable endpoint discovery.

Install

bash
npx -y @mambalabsdev/mcp-agent-accessibility-auditor

Claude Desktop

json
{  "mcpServers": {    "mamba-agent-accessibility-auditor": {      "command": "npx",      "args": ["-y", "@mambalabsdev/mcp-agent-accessibility-auditor"],      "env": { "APIFY_TOKEN": "your-apify-token" }    }  }}

Get an Apify token at console.apify.com/account/integrations.

Tool

audit_agent_accessibility

Domain in, whether an AI agent can read that site out.

InputTypeRequiredNotes
domainstringyesOne company domain, for example vercel.com. A full URL is accepted: the protocol and path are stripped. One domain per call.
checksarraynoRun only these checks: llms_txt, robots_ai, sitemap, openapi, security_txt, feeds, json_ld, microdata, open_graph, canonical, render_mode. Omit for all of them. A check you did not run reports null, never false, and the score is rescaled over what you selected.
check_endpointsbooleannoAlias for the checks array: false removes sitemap, openapi, security_txt and feeds. Ignored when checks is set. Default true.
check_structured_databooleannoAlias for the checks array: false removes json_ld, microdata, open_graph and canonical. Ignored when checks is set. Default true.
skipCacheenumnoLeave as false to use the 7 day cache. Set to true to re-audit the domain from scratch. Default false.
max_charge_usdnumbernoOptional cost cap in USD for this run. The actor stops before an item that could take its charges past this amount. Omit to rely on the maximum cost per run set in Apify.

Reading the output

Every field is a fact read off a fetch. No model is called at any point, so the same domain returns the same row today and next month unless the site actually changed.

has_llms_txt is true only when /llms.txt returns 200 and the body is real markdown, and llms_txt_reject_reason says why a 200 was not counted. Twelve requests per domain, robots.txt first and then the homepage and ten probes concurrently. Typical wall clock is 2 to 4 seconds.

Built for a technical SEO or growth engineer preparing a site for AI crawlers and agent traffic, or an agency selling that work and needing a before and after audit across a client list.

Billing

You are charged per domain analyzed, plus a small actor start fee. A repeat run inside the 7 day cache window costs nothing new.

Price per event on the Apify FREE plan, from the live pricing record; paid Apify plans pay less per event.

EventPrice (USD)
Domain analyzed (domain-analyzed)0.005
Actor Start (apify-actor-start)0.00005

Pricing is on the actor's Apify page. Running this server consumes Apify credits.

What this server does and does not do

It is a thin client for the Apify actor. It passes your input through and returns the actor's output unchanged. Every behavior described above lives in the actor, not here.

The tool starts the actor run and polls it to a finished status, so a long run is not cut off at 300 seconds. The run is allowed 1,800 seconds. If it is still going two minutes after that, the call stops waiting and returns the run ID with a link to it in the Apify Console, where the results land when it finishes. A run that does not succeed comes back as an error with its run ID and status.

Errors are surfaced, never swallowed. An invalid input, an invalid token, an exhausted balance, a timeout, or a run that returns anything other than a dataset all come back as an explicit tool error rather than as an empty result.

Source

The actor is on the Apify Store. This wrapper is MIT licensed.

Built by Mamba Labs

来源：README.md，提交 9b365e6

工具

1

audit_agent_accessibility

Audit Agent Accessibility

Checks whether an AI agent can read one website. Returns one flat row of 42 fields across five families: llms.txt (with llms-full.txt and ai.txt), robots.txt AI crawler policy including Content Signal directives, structured data (JSON-LD, microdata, Open Graph, canonical), render mode, and machine readable endpoints (sitemap, OpenAPI, well known files, feeds). Every field is read off a fetch and no model is called, so a repeat audit changes only when the site changes. Twelve requests per domain, typically 2 to 4 seconds. Use it to audit a site before and after AI crawler work, one domain per call. Do not use it to find which AI vendors a company pays for (that is the AI Tooling Detector) or to read page content. Requires an APIFY_TOKEN and consumes Apify credits: charged per domain analyzed plus a small run start fee. Reads public data only and writes nothing.

输入参数checksdomain必填skipCachemax_charge_usdcheck_endpointscheck_structured_data

版本历史

5
  1. v1.3.1最新Nov 5, 2026
  2. v1.3.0Oct 16, 2026
  3. v1.2.1Oct 6, 2026
  4. v1.2.0Oct 6, 2026
  5. v1.1.0Sep 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25 分
  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 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