Caelara Labs Web Intelligence 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.
Company intelligence: web metadata + DNS + MX in one call
Company domain, e.g. example.com
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 api https://api.caelaralabs.com/mcp
Company intelligence: web metadata + DNS + MX in one call
| Argument | Type | Description |
|---|---|---|
| domain* | string | Company domain, e.g. example.com |
{
"type": "object",
"required": [
"domain"
],
"properties": {
"domain": {
"type": "string",
"description": "Company domain, e.g. example.com"
}
}
}MX / provider forensics for an email address
| Argument | Type | Description |
|---|---|---|
| email* | string | Email address |
{
"type": "object",
"required": [
"email"
],
"properties": {
"email": {
"type": "string",
"description": "Email address"
}
}
}Parse HTML tables into JSON
| Argument | Type | Description |
|---|---|---|
| url | string | Page URL |
| html | string | Raw HTML (alternative to url) |
{
"type": "object",
"required": [],
"properties": {
"url": {
"type": "string",
"description": "Page URL"
},
"html": {
"type": "string",
"description": "Raw HTML (alternative to url)"
}
}
}Lead verification: email deliverability signals + LinkedIn URL checks
| Argument | Type | Description |
|---|---|---|
| email* | string | Lead email address |
| linkedin_url | string | LinkedIn profile URL |
{
"type": "object",
"required": [
"email"
],
"properties": {
"email": {
"type": "string",
"description": "Lead email address"
},
"linkedin_url": {
"type": "string",
"description": "LinkedIn profile URL"
}
}
}Scan a prompt for injection/PII and return a structured form
| Argument | Type | Description |
|---|---|---|
| prompt* | string | Prompt text |
| strict | boolean | Strict mode |
| context | string | Additional context |
{
"type": "object",
"required": [
"prompt"
],
"properties": {
"prompt": {
"type": "string",
"description": "Prompt text"
},
"strict": {
"type": "boolean",
"description": "Strict mode"
},
"context": {
"type": "string",
"description": "Additional context"
}
}
}Normalize RSS/Atom feeds to JSON
| Argument | Type | Description |
|---|---|---|
| url* | string | Feed URL |
| limit | integer | Max items (default 50) |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Feed URL"
},
"limit": {
"type": "integer",
"description": "Max items (default 50)"
}
}
}On-page SEO audit of a URL
| Argument | Type | Description |
|---|---|---|
| url* | string | Page URL |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Page URL"
}
}
}Parse a sitemap into a URL list
| Argument | Type | Description |
|---|---|---|
| url* | string | Sitemap or site URL |
| limit | integer | Max URLs (default 100) |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Sitemap or site URL"
},
"limit": {
"type": "integer",
"description": "Max URLs (default 100)"
}
}
}Extract OpenGraph / Twitter card metadata
| Argument | Type | Description |
|---|---|---|
| url* | string | Page URL |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Page URL"
}
}
}Convert a web page to clean Markdown
| Argument | Type | Description |
|---|---|---|
| url* | string | Page URL |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Page URL"
}
}
}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.