Mamba Labs 在 Apify 上的 Agent Accessibility Auditor actor 的 MCP 服务器。
AI 代理能读取这个网站吗？给它一个域名，它会返回一行包含 42 个字段的扁平数据，涵盖五类事实：llms.txt 类、robots AI 爬虫策略（包括较新的 Content Signal 指令）、结构化数据的存在与健康度、渲染模式，以及机器可读端点发现。
npx -y @mambalabsdev/mcp-agent-accessibility-auditor{
"mcpServers": {
"mamba-agent-accessibility-auditor": {
"command": "npx",
"args": ["-y", "@mambalabsdev/mcp-agent-accessibility-auditor"],
"env": { "APIFY_TOKEN": "your-apify-token" }
}
}
}在 console.apify.com/account/integrations 获取 Apify token。
Related MCP server: maxaeo-ai-visibility-mcp
audit_agent_accessibility输入域名，输出该网站是否可被 AI 代理读取。
输入 | 类型 | 必填 | 说明 |
| string | 是 | 一个公司域名，例如 vercel.com。协议和路径会被去除。 |
| array | 否 | 仅运行这些检查： |
| boolean | 否 |
|
| boolean | 否 |
|
| enum | 否 | 保持 |
每个字段都是从一次抓取中读取的事实。整个过程不会调用任何模型，因此同一个域名今天和下个月返回相同的行，除非网站真的发生了变化。
has_llms_txt 仅在 /llms.txt 返回 200 且正文是真正的 markdown 时才为 true，llms_txt_reject_reason 说明为什么某个 200 未被计入。每个域名发出十二个请求，先请求 robots.txt，然后并发请求首页和十个探测。典型墙钟耗时为 2 到 4 秒。
专为技术 SEO 或增长工程师打造，帮助他们让网站为 AI 爬虫和代理流量做好准备；也适用于销售此类服务、需要跨客户列表进行前后对比审计的代理机构。
按分析的每个域名计费，外加少量 actor 启动费。在 7 天缓存窗口内的重复运行不会产生新费用。
定价见 actor 的 Apify 页面。运行此服务器会消耗 Apify 积分。
它是 Apify actor 的轻量客户端。它透传你的输入并原样返回 actor 的输出。上述所有行为都存在于 actor 中，而不是这里。
错误会被暴露，绝不会被吞掉。无效输入、无效 token、余额耗尽、超时，或返回非数据集内容的运行，都会以明确的工具错误形式返回，而不是空结果。
actor 位于 Apify Store。此包装器采用 MIT 许可。
由 Mamba Labs 构建
Give it a domain and it returns whether an AI agent can read that site, and what the site's policy says, as one flat row of 42 fields across five families: the llms.txt family including llms-full.txt and ai.txt, robots.txt AI crawler policy including the newer Content Signal directives, structured data presence and health across JSON-LD, microdata, Open Graph and canonical, render mode, and machine readable endpoint discovery covering sitemap, OpenAPI, well known files and feeds. 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. Twelve requests per domain, typically 2 to 4 seconds. Built for a technical SEO or growth engineer preparing a site for AI crawlers, or an agency selling that work and needing a before and after audit across a client list. Requires an APIFY_TOKEN and consumes Apify credits. Read only.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | One company domain, for example vercel.com. Protocol and path are stripped. | |
| skipCache | No | Leave as false to use the 7 day cache. Set to true to re-audit the domain from scratch. Default: "false". | |
| check_endpoints | No | Probes sitemap, OpenAPI, well known files and feeds. Adds 7 concurrent requests. Default: true. | |
| check_structured_data | No | Parses JSON-LD, microdata, Open Graph and canonical off the homepage. Costs no extra requests. Default: true. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds substantial behavioral context beyond the annotations: 'No model is called at any point', 'same domain returns the same row today and next month unless the site actually changed', 'Twelve requests per domain, typically 2 to 4 seconds', and 'Read only'. It also discloses resource consumption and auth needs, aligning with the annotations without contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is relatively long but every sentence adds value: it covers output structure, behavior, performance, use case, and requirements. It is front-loaded with the core purpose and then expands into detail. Minor verbosity exists, but it is well-organized and not redundant.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having no output schema, the description thoroughly describes the return value as a flat row of 42 fields across five named families. It also covers deterministic behavior, request count, latency, auth, and intended audience. For a complex tool with 4 parameters and detailed output, this is highly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, so the baseline is 3. The description does not add parameter-specific details beyond what the schema already provides, but it does reference the overall request count and endpoint checks, slightly reinforcing the check_endpoints/check_structured_data semantics. This is sufficient given the schema's thoroughness.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool's function: 'Give it a domain and it returns whether an AI agent can read that site, and what the site's policy says'. It also enumerates the output families, providing a specific verb+resource+scope. Even without siblings, it is clearly differentiated from generic audit tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description names the target user ('technical SEO or growth engineer', 'agency') and use case ('preparing a site for AI crawlers', 'before and after audit'). It also mentions prerequisites (APIFY_TOKEN, credits). However, it does not explicitly state when not to use the tool or mention alternatives, which is acceptable given there are no siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of confusion or overlap. The tool's purpose is clearly defined and distinct by virtue of being the sole member of the set.
The single tool name follows a clear verb_noun pattern (audit_agent_accessibility), consistent with common MCP naming conventions. There are no other tools to conflict with this pattern.
A single tool feels minimal for a server, but the tool itself is highly specialized and performs a comprehensive audit in one action. The count is borderline, as it could benefit from additional tools like listing domains or comparing audits, but the narrow scope partially justifies the thin surface.
For the stated purpose of auditing agent accessibility, the tool covers a wide range of signals (llms.txt, robots.txt, structured data, render mode, endpoint discovery) in a single output. The only gap is the lack of supporting operations, but as a read-only audit tool, the core domain is well covered.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Checks llms.txt, AI crawler access in robots.txt, and sitemap - with a 0-100 AI readiness score.
Scan any public site for AI-agent visibility; get scored findings, a machine-readable fix pack, and
Generate 18 AI readiness files (llms.txt, ai.txt, RAG indexes, schema) for any website.
AEO audit: score any website 0-100 for AI visibility. Checks schema, meta, content, AI crawlers.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mambalabsdev/mcp-agent-accessibility-auditor'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
