MCP Dharmamitra runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 12 Sep 2026.
Dharmamitra OCR for Tibetan / Sanskrit / Devanagari images; writes extracted text to a file.
Today is the operative word: we check MCP Dharmamitra every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-dharmamitra -- uvx mcp-dharmamitra
{
"mcpServers": {
"mcp-dharmamitra": {
"args": [
"mcp-dharmamitra"
],
"command": "uvx"
}
}
}
[mcp_servers.mcp-dharmamitra]
command = "uvx"
args = ["mcp-dharmamitra"]
{
"mcpServers": {
"mcp-dharmamitra": {
"args": [
"mcp-dharmamitra"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"mcp-dharmamitra": {
"args": [
"mcp-dharmamitra"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
DHARMAMITRA_COOKIE (Optional cf_clearance cookie value. Only needed if requests start returning 403 from Cloudflare.).
The author declared them in the registry entry; get the values from the project itself.
OCR and document understanding: extract text from images, then summarize or translate it.
File operations for AI agents: PDF, extraction, OCR, images. $0.01/op, 100 free.
PDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages.
Extract text from documents, manipulate PDFs, and perform OCR on images.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
OCR.space MCP — wraps the OCR.space API (ocr.space) for image/PDF → text OCR.
MCP server for extracting text, images, tables, links, annotations, and metadata from PDF files.
One section in, one section out — on Markdown/GEML files, bad writes refused.
Answers built from our own checks of this server.