# Lexyholdcraft Source Agent Tools Uk MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.lexyholdcraft-source%2Fagent-tools-uk
Registry id: `mcp-registry/io.github.lexyholdcraft-source/agent-tools-uk`
Status: live (checked 2026-11-22T15:16:57.143Z)

## Measurements (30 days)

- Uptime: 100%
- Checks: 754
- Outages (90 days): 0

## Install

```json
{
  "mcpServers": {
    "lexyholdcraft-source-agent-tools-uk-mcp-": {
      "type": "http",
      "url": "https://agent-tools-production-e6aa.up.railway.app/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http lexyholdcraft-source-agent-tools-uk-mcp- https://agent-tools-production-e6aa.up.railway.app/mcp
```

## Tools (18)

- `broken_link_check`: Find broken links on a web page: collects every link on the page and checks each one (up to 200, in parallel), returning the broken ones with their status code 
- `convert_file`: Convert office documents and images between formats. Documents (docx, doc, xlsx, xls, pptx, ppt, odt, rtf, html, txt, csv) to pdf, docx, odt, txt, xlsx or csv; 
- `document_to_json`: Read a whole document in one call: all the text (OCR for scans and photos, exact text for digital PDFs) plus every table as rows of cells. Use when processing i
- `domain_dns_lookup`: Look up a domain in one call: DNS records (A, AAAA, MX, NS, TXT, CAA, SOA), email security (SPF, DMARC and its policy) and registration from RDAP (registrar, cr
- `extract_structured_data`: Pull the machine-readable facts from a web page: schema.org JSON-LD and microdata, products with prices, currency, availability and ratings, the organisation's 
- `html_to_pdf`: Turn HTML you write (an invoice, report, letter or certificate) or a public web page into a print-quality PDF, rendered by Chrome with backgrounds and CSS. Use 
- `ocr_batch`: Read the text from up to 10 images, scans or PDFs in one paid call, cheaper than one call per file. Use for a stack of receipts, pages of a scanned letter, phot
- `ocr_read_text`: Read the text from a photo, screenshot, scan or scanned PDF (OCR). If the PDF already has real text, that is returned instead (faster and exact). Use when text 
- `page_change_check`: Check whether a web page has changed since you last looked. Returns the page's main text and a fingerprint (hash); send back previous_hash to get changed true/f
- `pdf_tables_to_json`: Extract every table from a PDF and return it as rows of cells in JSON, with the page number of each table. Use when you need numbers from financial statements, 
- `screenshot_webpage`: Render any public web page in a real Chrome browser and return a PNG screenshot. Use when you need to see how a page looks, check a layout, capture visual evide
- `seo_page_audit`: Audit a web page's SEO and sharing tags in one call: title and meta description (with lengths), canonical, robots/noindex, lang, viewport, H1/H2 headings, word 
- `sitemap_reader`: List a website's pages from its sitemap: reads robots.txt (sitemaps, allow/disallow rules for all crawlers, crawl-delay), then the sitemap(s), following sitemap
- `transcribe_audio`: Speech to text: turn a voice note, phone call, meeting recording, podcast clip or video (mp3, m4a, wav, ogg, mp4, webm, up to 15 minutes) into text with timesta
- `uk_company_check`: Verify a UK business on the official Companies House register by company NAME or NUMBER: legal name, status (active, dissolved, liquidation), type, incorporatio
- `uk_postcode_lookup`: Look up any UK postcode and get latitude/longitude, local council, county, ward, parish, parliamentary constituency, region and country, from official ONS data.
- `webpage_to_markdown`: Fetch a public web page and return just the main article as clean Markdown, with title, byline and excerpt. Menus, ads and footers are removed. Use when you nee
- `website_status_check`: Check whether a website is up right now: HTTP status, response time in ms, full redirect chain, and the SSL certificate's validity, issuer and days until expiry

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
