Caelara Labs SEO & GEO Readiness tools over remote MCP. Pay-per-call via x402 USDC or API key.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Check whether GPTBot, PerplexityBot, Google-Extended and other AI crawlers are allowed by robots.txt
URL (path is evaluated against robots.txt)
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http seo https://seo.caelaralabs.com/mcp
Check whether GPTBot, PerplexityBot, Google-Extended and other AI crawlers are allowed by robots.txt
| Argument | Type | Description |
|---|---|---|
| url* | string | URL (path is evaluated against robots.txt) |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "URL (path is evaluated against robots.txt)"
}
}
}Check outbound and internal links on a page for 4xx/5xx and dead hosts
| Argument | Type | Description |
|---|---|---|
| url* | string | Page URL |
| max_links | integer | Max links to check 1-40 (default 25) |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Page URL"
},
"max_links": {
"type": "integer",
"description": "Max links to check 1-40 (default 25)"
}
}
}Generative-engine readiness score: llms.txt + AI crawler access + structured data + content clarity
| Argument | Type | Description |
|---|---|---|
| url* | string | Page URL to assess |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Page URL to assess"
}
}
}Validate hreflang annotations: codes, x-default, self-reference and optional return links
| Argument | Type | Description |
|---|---|---|
| url* | string | Page URL |
| check_return_links | boolean | Verify reciprocal links on up to 5 alternates (true/false) |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Page URL"
},
"check_return_links": {
"type": "boolean",
"description": "Verify reciprocal links on up to 5 alternates (true/false)"
}
}
}Extract top keyword unigrams, bigrams and trigrams with density
| Argument | Type | Description |
|---|---|---|
| top | integer | Results per n-gram size (default 15) |
| text* | string | Text to analyze |
| max_n | integer | Largest n-gram size 1-3 (default 3) |
| include_stopwords | boolean | Keep stopword-edged phrases |
{
"type": "object",
"required": [
"text"
],
"properties": {
"top": {
"type": "integer",
"description": "Results per n-gram size (default 15)"
},
"text": {
"type": "string",
"description": "Text to analyze"
},
"max_n": {
"type": "integer",
"description": "Largest n-gram size 1-3 (default 3)"
},
"include_stopwords": {
"type": "boolean",
"description": "Keep stopword-edged phrases"
}
}
}Fetch and audit /llms.txt (and llms-full.txt) against the llms.txt format
| Argument | Type | Description |
|---|---|---|
| url* | string | Any URL on the target site |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Any URL on the target site"
}
}
}Trace a redirect chain hop by hop with loop detection and status issues
| Argument | Type | Description |
|---|---|---|
| url* | string | Starting URL |
| max_hops | integer | Max hops 1-10 (default 10) |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Starting URL"
},
"max_hops": {
"type": "integer",
"description": "Max hops 1-10 (default 10)"
}
}
}Extract and validate JSON-LD / microdata structured data on a page
| Argument | Type | Description |
|---|---|---|
| url* | string | Page URL |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Page URL"
}
}
}Pixel-width SERP snippet preview with truncation for desktop and mobile
| Argument | Type | Description |
|---|---|---|
| url | string | Display URL |
| title* | string | Page title |
| description | string | Meta description |
{
"type": "object",
"required": [
"title"
],
"properties": {
"url": {
"type": "string",
"description": "Display URL"
},
"title": {
"type": "string",
"description": "Page title"
},
"description": {
"type": "string",
"description": "Meta description"
}
}
}Technical SEO audit: redirects, meta, canonical, headings, hreflang, schema, robots.txt with scored issues
| Argument | Type | Description |
|---|---|---|
| url* | string | Page URL to audit |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Page URL to audit"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 19, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.