INDIVIDUAL MCP TOOL
extract_text_ocr
Read text off an IMAGE by optical character recognition — photos, screenshots and scans.
LIVE ENDPOINT
https://www.razi.pro/api/mcp
Connect to this endpoint to inspect the live schema for extract_text_ocr and invoke it with your own arguments.
Indexed input schema
{}Risk classification
Inferred read-only · medium confidence · heuristic, not a guarantee.
- No write-capable action terms were found; this is not proof that invocation has no side effects.
Parent server
CONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.razi-tools]
url = "https://www.razi.pro/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"razi-tools": {
"type": "http",
"url": "https://www.razi.pro/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: razi-tools
Remote MCP URL: https://www.razi.pro/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"razi-tools": {
"url": "https://www.razi.pro/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"razi-tools": {
"type": "http",
"url": "https://www.razi.pro/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "razi-tools",
"transport": "streamable-http",
"url": "https://www.razi.pro/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
Related tools
merge_pdf— Concatenate two or more PDFs into a single PDF, in the order supplied, and return the merged file.split_pdf— Extract page ranges from one PDF into new PDFs.compress_pdf— Shrink a PDF's byte size while keeping it a PDF, for email limits or slow connections.compress_image— Re-encode a single raster image to webp, jpeg, png or avif, optionally resizing it and/or converting it to grayscale.shorten_url— Create a permanent razi.screenshot_url— Capture a screenshot of any public web page, rendered in a real headless browser so JavaScript, web fonts and lazy-loaded images all appear.fetch_site_logo— Get a company's logo from its website URL.fetch_page_metadata— Read a web page's metadata without downloading any images: title, description, siteName, canonical URL, language, theme colour, generator, RSS/Atom feeds, and the full OpenGraph and Twitter card tag sets.