Caelara Labs Document Utilities 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.
Normalize a postal address: casing, street/directional abbreviations, unit, ZIP and state
Free-form address
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 docs https://docs.caelaralabs.com/mcp
Normalize a postal address: casing, street/directional abbreviations, unit, ZIP and state
| Argument | Type | Description |
|---|---|---|
| address* | string | Free-form address |
{
"type": "object",
"required": [
"address"
],
"properties": {
"address": {
"type": "string",
"description": "Free-form address"
}
}
}Parse CSV into JSON rows with inferred number, boolean, null and date types
| Argument | Type | Description |
|---|---|---|
| csv* | string | CSV text |
| header | boolean | First row is header (default true) |
| delimiter | string | Delimiter (auto-detected if omitted) |
{
"type": "object",
"required": [
"csv"
],
"properties": {
"csv": {
"type": "string",
"description": "CSV text"
},
"header": {
"type": "boolean",
"description": "First row is header (default true)"
},
"delimiter": {
"type": "string",
"description": "Delimiter (auto-detected if omitted)"
}
}
}Cluster near-duplicate strings using Jaro-Winkler and token similarity
| Argument | Type | Description |
|---|---|---|
| items* | array | Array of strings |
| threshold | number | Similarity threshold 0.5-1 (default 0.88) |
{
"type": "object",
"required": [
"items"
],
"properties": {
"items": {
"type": "array",
"description": "Array of strings"
},
"threshold": {
"type": "number",
"description": "Similarity threshold 0.5-1 (default 0.88)"
}
}
}Strip HTML to readable plain text, dropping scripts, styles and tags
| Argument | Type | Description |
|---|---|---|
| html* | string | HTML text |
| keep_links | boolean | Append link URLs in brackets |
{
"type": "object",
"required": [
"html"
],
"properties": {
"html": {
"type": "string",
"description": "HTML text"
},
"keep_links": {
"type": "boolean",
"description": "Append link URLs in brackets"
}
}
}Convert raw invoice text into structured JSON: number, dates, currency, line items, totals and consistency checks
| Argument | Type | Description |
|---|---|---|
| text* | string | Raw invoice text |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "Raw invoice text"
}
}
}Render markdown to HTML with all raw HTML escaped and unsafe URLs removed
| Argument | Type | Description |
|---|---|---|
| markdown* | string | Markdown text |
{
"type": "object",
"required": [
"markdown"
],
"properties": {
"markdown": {
"type": "string",
"description": "Markdown text"
}
}
}Format a phone number to E.164 with country detection and validity check
| Argument | Type | Description |
|---|---|---|
| phone* | string | Phone number |
| country | string | Default ISO-2 country code, e.g. US |
{
"type": "object",
"required": [
"phone"
],
"properties": {
"phone": {
"type": "string",
"description": "Phone number"
},
"country": {
"type": "string",
"description": "Default ISO-2 country code, e.g. US"
}
}
}Extract emails, URLs, phones, IPs, dates, money, hashtags, mentions and more from text
| Argument | Type | Description |
|---|---|---|
| text* | string | Text to scan |
| types | array | Entity types to extract (array of strings) |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "Text to scan"
},
"types": {
"type": "array",
"description": "Entity types to extract (array of strings)"
}
}
}Convert data between CSV, XML and JSON with format auto-detection and type inference
| Argument | Type | Description |
|---|---|---|
| to* | string | Target format: json|csv|xml |
| data* | string | Input document (string) or JSON value |
| from | string | Source format: auto|csv|xml|json (default auto) |
{
"type": "object",
"required": [
"data",
"to"
],
"properties": {
"to": {
"type": "string",
"description": "Target format: json|csv|xml"
},
"data": {
"type": "string",
"description": "Input document (string) or JSON value"
},
"from": {
"type": "string",
"description": "Source format: auto|csv|xml|json (default auto)"
}
}
}Convert XML to clean JSON (attributes prefixed with @, repeated tags to arrays)
| Argument | Type | Description |
|---|---|---|
| xml* | string | XML text |
{
"type": "object",
"required": [
"xml"
],
"properties": {
"xml": {
"type": "string",
"description": "XML text"
}
}
}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.