Apify의 Mamba Labs Agent Accessibility Auditor 액터를 위한 MCP 서버입니다.
AI 에이전트가 이 사이트를 읽을 수 있을까요? 도메인을 입력하면 42개 필드로 이루어진 단일 행을 반환하며, 다섯 가지 사실 범주를 다룹니다: llms.txt 계열, 최신 Content Signal 지시문을 포함한 robots AI 크롤러 정책, 구조화 데이터의 존재 여부와 상태, 렌더링 모드, 그리고 기계가 읽을 수 있는 엔드포인트 탐색입니다.
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" }
}
}
}Apify 토큰은 console.apify.com/account/integrations에서 받으세요.
Related MCP server: maxaeo-ai-visibility-mcp
audit_agent_accessibility도메인을 입력하면 해당 사이트를 AI 에이전트가 읽을 수 있는지 여부를 출력합니다.
입력 | 유형 | 필수 | 설명 |
| string | 예 | 회사 도메인 하나, 예를 들어 vercel.com. 프로토콜과 경로는 제거됩니다. |
| array | 아니요 | 다음 검사만 실행합니다: |
| boolean | 아니요 | checks 배열의 별칭: false로 설정하면 |
| boolean | 아니요 | checks 배열의 별칭: false로 설정하면 |
| enum | 아니요 | 7일 캐시를 사용하려면 |
모든 필드는 fetch에서 읽어낸 사실입니다. 어떤 시점에서도 모델이 호출되지 않으므로, 사이트가 실제로 변경되지 않는 한 같은 도메인은 오늘과 다음 달에도 동일한 행을 반환합니다.
has_llms_txt는 /llms.txt가 200을 반환하고 본문이 실제 마크다운일 때만 true이며, llms_txt_reject_reason은 200이 집계되지 않은 이유를 알려줍니다. 도메인당 12개의 요청이 전송되며, robots.txt를 먼저 요청한 다음 홈페이지와 10개의 프로브를 동시에 요청합니다. 일반적인 실제 소요 시간은 2~4초입니다.
AI 크롤러와 에이전트 트래픽에 대비해 사이트를 준비하는 기술 SEO 또는 그로스 엔지니어, 또는 그러한 작업을 판매하면서 고객 목록 전체에 대한 감사 전후 결과가 필요한 에이전시를 위해 만들어졌습니다.
분석한 도메인당 요금이 부과되며, 여기에 소액의 액터 시작 수수료가 추가됩니다. 7일 캐시 기간 내에 다시 실행하면 추가 비용이 발생하지 않습니다.
가격은 액터의 Apify 페이지에서 확인할 수 있습니다. 이 서버를 실행하면 Apify 크레딧이 소모됩니다.
Apify 액터를 위한 경량 클라이언트입니다. 입력을 그대로 전달하고 액터의 출력을 변경 없이 반환합니다. 위에서 설명한 모든 동작은 여기가 아니라 액터에 구현되어 있습니다.
오류는 결코 삼켜지지 않고 표면화됩니다. 잘못된 입력, 유효하지 않은 토큰, 잔액 부족, 시간 초과, 또는 데이터셋이 아닌 다른 것을 반환하는 실행은 모두 빈 결과가 아닌 명시적인 도구 오류로 반환됩니다.
액터는 Apify Store에 있습니다. 이 래퍼는 MIT 라이선스로 제공됩니다.
Mamba Labs가 만들었습니다.
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
