Site SEO & AI Crawler Audit

Check AI crawler access in robots.txt

check_ai_crawler_access

Read-onlyIdempotent

Checks whether 14 AI crawlers may fetch a page. Use it when the user asks whether AI crawlers can read a website or page, for example "can AI crawlers read example.com?", "is GPTBot blocked in my robots.txt?" or "which AI bots are allowed on https://example.com/blog?". Pass the page address. Returns, for 14 AI crawlers, whether robots.txt allows the page and the rule that decided it, plus the sitemaps, the redirect chain, and the page's X-Robots-Tag header and robots meta tag. It reads robots.txt only and does not test whether a firewall blocks crawlers. Do not use it for private or local addresses, for security scans, or to collect a site's content.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes	Address of a public web page, for example https://example.com/pricing. A bare domain such as example.com means https. Only public http and https sites on the standard ports are checked.

Output Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	The address checked, after a bare domain became https.
`notes`	No	Plain-language caveats to pass on with the result.
`notice`	Yes	As-of caveat: what the site sent to Agent Tools at that moment, not what every crawler sees.
`robots`	No
`source`	Yes	Where the data came from: the website itself.
`status`	No	HTTP status code of the final page.
`failure`	No	Why the page was not reached or read, such as a timeout or a refused redirect.
`crawlers`	No
`finalUrl`	No	Address of the final page after redirects.
`reachable`	Yes	False when no page answered; failure then says why.
`redirects`	No	Redirect chain from the address to the page.
`metaRobots`	No	The page's robots meta tag.
`xRobotsTag`	No	The page's X-Robots-Tag response header.
`blockedCrawlers`	No	Tokens of the crawlers robots.txt blocks on this page.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 13, 2026

changedOutput schema / properties / robots / properties / status / description

Previous value: -"found: rules were read. missing: a 4xx answer, so nothing is restricted. unreachable: a 5xx or no answer, so there is no verdict."New value: +"found: rules were read. missing: a 4xx answer, so nothing is restricted. unreachable: a 5xx, no answer, or a web page instead of a robots file, so there is no verdict."

Changed24 schema fields changedOct 12, 2026

addedOutput schema / properties / blockedCrawlers / description

Added value: +"Tokens of the crawlers robots.txt blocks on this page."

addedOutput schema / properties / crawlers / items / properties / allowed / description

Added value: +"Whether robots.txt allows this crawler on the page. null means robots.txt could not be read, so there is no verdict."

addedOutput schema / properties / crawlers / items / properties / crawler / description
```
Added value: +"User-agent token, such as GPTBot."
```
addedOutput schema / properties / crawlers / items / properties / operator / description
```
Added value: +"Company that runs the crawler."
```
addedOutput schema / properties / crawlers / items / properties / purpose / description
```
Added value: +"What the crawler collects for, such as training or search."
```
addedOutput schema / properties / crawlers / items / properties / rule / description
```
Added value: +"The robots.txt line that decided it, such as Disallow: /."
```

addedOutput schema / properties / failure / description

Added value: +"Why the page was not reached or read, such as a timeout or a refused redirect."

addedOutput schema / properties / finalUrl / description

Added value: +"Address of the final page after redirects."

addedOutput schema / properties / metaRobots / description
```
Added value: +"The page's robots meta tag."
```

addedOutput schema / properties / notes / description

Added value: +"Plain-language caveats to pass on with the result."

addedOutput schema / properties / notice / description

Added value: +"As-of caveat: what the site sent to Agent Tools at that moment, not what every crawler sees."

addedOutput schema / properties / reachable / description

Added value: +"False when no page answered; failure then says why."

addedOutput schema / properties / redirects / description

Added value: +"Redirect chain from the address to the page."

addedOutput schema / properties / redirects / items / properties / location / description
```
Added value: +"Location header of a redirect hop: where it points next."
```
addedOutput schema / properties / redirects / items / properties / status / description
```
Added value: +"HTTP status code of this hop, such as 301 or 200."
```
addedOutput schema / properties / redirects / items / properties / url / description
```
Added value: +"Address requested at this hop."
```
addedOutput schema / properties / robots / properties / httpStatus / description
```
Added value: +"HTTP status code of robots.txt."
```
addedOutput schema / properties / robots / properties / sitemaps / description
```
Added value: +"Sitemap addresses listed in robots.txt."
```

addedOutput schema / properties / robots / properties / status / description

Added value: +"found: rules were read. missing: a 4xx answer, so nothing is restricted. unreachable: a 5xx or no answer, so there is no verdict."

addedOutput schema / properties / robots / properties / url / description
```
Added value: +"Address of robots.txt."
```

addedOutput schema / properties / source / description

Added value: +"Where the data came from: the website itself."

addedOutput schema / properties / status / description

Added value: +"HTTP status code of the final page."

addedOutput schema / properties / url / description

Added value: +"The address checked, after a bare domain became https."

addedOutput schema / properties / xRobotsTag / description

Added value: +"The page's X-Robots-Tag response header."

Changed1 schema field changedOct 5, 2026

removedOutput schema / properties / note_from_openkrill

Removed value: -{
-  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
-  "type": "string"
-}

Changed1 schema field changedOct 4, 2026

addedOutput schema / properties / note_from_openkrill

Added value: +{
+  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
+  "type": "string"
+}

First observedOct 3, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive). The description adds real behavioral context beyond them: it reads robots.txt only and explicitly does NOT test firewall blocking, and it enumerates what is returned (rules, sitemaps, redirect chain, X-Robots-Tag, meta tag). Missing only rate-limit/auth notes, which are minor for a public read tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then usage examples, returns, and exclusions in a logical order. Every sentence is functional, though the return-value enumeration is somewhat redundant given an output schema exists and the example queries could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a rich output schema and full annotations already present, the description still supplies the missing pieces an agent needs: trigger phrasing, hard exclusions, and the scope limitation about firewalls. Nothing material is absent for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 is already fully documented (format, https default, port restriction). The description's 'Pass the page address' adds no syntax or format meaning beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Checks whether 14 AI crawlers may fetch a page') and clarifies it reads robots.txt only, which distinguishes it from sibling tools like trace_redirects or check_page_tags. An agent can identify its scope without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit trigger conditions with example user questions ('can AI crawlers read example.com?', 'is GPTBot blocked?') plus concrete exclusions (not for private/local addresses, security scans, or content collection). This is close to a full when/when-not specification.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Site SEO & AI Crawler Audit tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.