robots.txt tester (RFC 9309), AI crawler access (GPTBot, ClaudeBot...) and sitemap check.
Scored across 3 tools
The three tools target distinct artifacts (AI-crawler token report, RFC 9309 single-token robots evaluation, sitemap validation), but robots_check and ai_crawler_access both fetch robots.txt and return access verdicts, so an agent could misselect between the generic and AI-specific checks. Descriptions clarify the difference (single UA token vs 20 AI tokens plus meta/llms.txt), which keeps the overlap tolerable.
All names are snake_case with a consistent <subject>_check/access pattern (robots_check, sitemap_check, ai_crawler_access). It is a noun_action convention rather than strict verb_noun, and ai_crawler_access breaks the *_check suffix slightly, but the set reads consistently.
Three tools is borderline thin for a checker whose stated scope spans robots.txt, AI crawlers, and sitemaps. Each tool earns its place, but there is little room for adjacent operations (e.g. bulk URL checks or llms.txt inspection), making the surface feel minimal.
The set covers the core lifecycle of crawl-permission assessment: single-token RFC 9309 evaluation, broad AI-crawler token analysis with meta/X-Robots/llms.txt signals, and sitemap discovery plus validation. Minor gaps remain (llms.txt is only presence-checked, no bulk/multi-URL mode), but no major dead ends.
AI crawler access report for a URL: robots.txt verdict for 20 tokens (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, Claude-User, Google-Extended, Applebot-Extended, PerplexityBot, Meta-ExternalAgent, CCBot, Bytespider, Amazonbot and more) grouped by training/search/user purpose, plus page meta robots, X-Robots-Tag (noindex/noai) and llms.txt presence. Deterministic, no AI. Price: $0.002 USDC per call via x402 (Base); the first 5 calls per day per client are free.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Site or page URL |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds meaningful behavioral context: it is deterministic and uses no AI, and it discloses the payment model ($0.002 USDC per call via x402 on Base) plus a free tier (first 5 calls per day per client). This cost/auth information directly affects invocation and selection decisions, though rate limits beyond the free tier and error behavior are not covered.
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 front-loaded with purpose and output scope, followed by a compact pricing sentence. The long token enumeration is informative but slightly overstuffed; it earns its place by demonstrating coverage of major AI crawlers. Overall the structure is efficient and each sentence serves a clear function.
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?
With no output schema, the description successfully enumerates what the report contains (robots.txt verdicts by token group, meta robots, X-Robots-Tag, llms.txt). It also covers determinism and cost, which are important for an external-fetch tool. It is missing only minor operational details such as timeout or error handling, so it is nearly complete for correct invocation.
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?
Schema description coverage is 100%; the single parameter 'url' is fully documented in the schema with a description and example. The tool description adds no syntax, format, or constraint details beyond saying 'for a URL'. Baseline 3 is appropriate when the schema already carries parameter semantics.
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 states a specific verb ('access report') and resource ('AI crawler access for a URL'), and enumerates exactly what is checked (robots.txt verdicts for 20 AI tokens, meta robots, X-Robots-Tag, llms.txt). This scope clearly separates it from the sibling robots_check (a general robots.txt tool) and sitemap_check. An agent can tell what this tool returns without opening any schema.
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 implies usage by describing the exact scenario (checking AI crawler permissions for a URL) but never explicitly states when to choose it over robots_check or sitemap_check. It adds practical selection context through pricing and free-tier notes, but offers no exclusions or direct alternatives. A 3 reflects clearly implied but unguided usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Crawl-permission preflight for agents and scrapers: fetches the site's robots.txt and evaluates the URL for a user-agent token per RFC 9309 (group by product token else *, longest match, Allow wins ties, * and $ wildcards, 4xx=allow all, 5xx=disallow all). Returns allowed, the deciding rule and line, crawl-delay and sitemaps. Deterministic, no AI. Price: $0.001 USDC per call via x402 (Base); the first 5 calls per day per client are free.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Page URL to test | |
| user_agent | No | Crawler product token, e.g. GPTBot or MyAgent. Default * |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing the cost model ($0.001 USDC via x402 on Base, first 5 calls/day free), the determinism guarantee (no AI), and the error semantics (4xx=allow all, 5xx=disallow all). It also states the exact matching rules, so the agent knows how results are derived rather than trusting a black box.
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?
Purpose is front-loaded, and the dense RFC parenthetical and price clause each carry information an agent needs. It is slightly clause-heavy but nothing is repeated or wasted.
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?
With no output schema, the description correctly enumerates the return payload (allowed, deciding rule and line, crawl-delay, sitemaps). Combined with pricing, error handling, and matching semantics, an agent has everything needed to decide to call it and interpret the result.
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?
Schema coverage is 100% and both parameter descriptions are adequate, so the baseline is 3. The description adds real value on top by explaining how user_agent is interpreted (group by product token else '*', longest match, Allow wins ties), which the schema's one-line description does not convey.
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 gives a specific verb and resource: it fetches robots.txt and evaluates a URL for a given user-agent token under RFC 9309. That is far more precise than a generic 'check' tool. It does not, however, explicitly distinguish itself from the sibling tools ai_crawler_access and sitemap_check, which an agent could plausibly confuse with this one.
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 framing 'Crawl-permission preflight for agents and scrapers' makes the use context clear: run it before crawling a URL. It states no explicit exclusions or alternatives, so an agent must infer whether ai_crawler_access or sitemap_check is the better fit in a given situation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Finds a site's sitemap (from robots.txt, else /sitemap.xml) or checks the sitemap URL given, and validates it: urlset vs sitemapindex, entry count against the 50,000 limit, lastmod format and range, relative/off-host/duplicate/http URLs, gzip support. Returns sample URLs or child sitemaps. Deterministic, no AI. Price: $0.002 USDC per call via x402 (Base); the first 5 calls per day per client are free.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Site URL (discovers the sitemap) or a sitemap URL |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses determinism (no AI), the discovery fallback chain (robots.txt, else /sitemap.xml), the exact validation checks performed, and the auth/cost model (x402 USDC payment on Base, first 5 calls/day free). That pricing and rate-limit detail is genuinely useful pre-invocation context.
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?
Front-loaded with the core action and discovery logic, then validation specifics, return format, and cost in descending priority. Every clause carries information, though the validation list is dense enough to read as a run-on.
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?
With no output schema, the description compensates by stating what is returned (sample URLs or child sitemaps) plus the validation semantics and payment/auth requirements. An agent has everything needed to call it correctly and interpret the result.
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?
Schema description coverage is 100% and the single url parameter's dual meaning (site URL vs sitemap URL) is already stated verbatim in the schema. The description restates the same dual mode without adding syntax, format, or edge-case detail beyond it, so baseline 3 applies.
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?
States specific verbs and resource: finds a site's sitemap or validates a given sitemap URL, and enumerates exactly what is validated (urlset vs sitemapindex, entry count, lastmod, gzip). This clearly distinguishes it from robots_check (which parses robots.txt) even though only the discovery fallback references robots.txt.
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?
Gives clear context for both invocation modes: pass a site URL to discover the sitemap, or pass a sitemap URL to check it directly. However, it never names robots_check or ai_crawler_access as alternatives or states when this tool is the wrong choice, so it stops short of explicit routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
ai_crawler_accessrobots_checksitemap_checkGenerate, validate and check robots.txt rules for AI crawlers. Free; optional Pro key.
Check which AI crawlers a site allows and see pages the way AI crawlers do. Free, read-only.
Checks llms.txt, AI crawler access in robots.txt, and sitemap - with a 0-100 AI readiness score.
Free check whether a website is technically open to AI assistants (AI crawlers, llms.txt, JSON-LD).
Add one secure layer between your agents and this server.