pdf-translate MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@pdf-translate MCPStart a job to translate a 50-page French PDF to English"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
pdf-translate MCP
Local MCP server for Claude Desktop that runs the full pdf-translate pipeline:
extract.py → parallel API translation → check.py → apply.py
Install
cd D:\Internship\skill\pdf-translate-mcp
pip install -r requirements.txtParent scripts (extract.py, check.py, apply.py) live in D:\Internship\skill\ and are called automatically.
Related MCP server: Local Development MCP Server
Claude Desktop config
Edit %APPDATA%\Claude\claude_desktop_config.json — merge into existing mcpServers:
"pdf-translate": {
"command": "C:\\Users\\neelima\\Anaconda3\\python.exe",
"args": ["D:\\Internship\\skill\\pdf-translate-mcp\\server.py"],
"env": {
"ANTHROPIC_API_KEY": "sk-ant-YOUR_KEY_HERE"
}
}Fully quit Claude Desktop (tray → Exit), reopen, start a new chat.
Tools
Tool | When to use |
| Recommended for 50-page PDFs. Returns |
| Poll every 15–30s until |
| Small/fast one-shot jobs only (Desktop kills tools after ~4 min). |
| Tiny PDFs only (~<750KB raw). |
Example prompt (job-based — use this for 50 pages)
Call
start_translate_pdf_jobonC:\Users\neelima\Downloads\50_pages_french.pdfwithtarget_langen andoutput_pathC:\Users\neelima\Downloads\50_pages_french_en.pdf. Pollget_translate_pdf_jobevery 20 seconds until done. Reportstats.timing_sand wall-clock time.
Example prompt (blocking path — small PDFs only)
Call
translate_pdf_pathonC:\Users\neelima\Downloads\small.pdfwithtarget_langen.
Base64 limit
Do not use translate_pdf_base64 for multi-page PDFs in Desktop. read_media_file and tool results are capped at 1MB; a 1.09 MB PDF becomes ~1.5M chars of base64 and fails before translation starts.
Local test (no Claude)
# Extract only (no API key)
python tests\test_pipeline_local.py --extract-only "C:\Users\neelima\Downloads\50_pages_french.pdf"
# Full pipeline (needs ANTHROPIC_API_KEY)
$env:ANTHROPIC_API_KEY = "sk-ant-..."
python tests\test_pipeline_local.py "C:\Users\neelima\Downloads\50_pages_french.pdf" -t enJob artifacts: pdf-translate-mcp/runs/<job_id>/
Timing (typical 50-page doc)
Stage | ~seconds |
extract | 2–5 |
translate | 45–60 |
check | <1 |
apply | 35–45 |
total | ~85–110 |
Troubleshooting
“Linux cloud VM” / paths not reachable / no translate_pdf_path
You are almost certainly in Cowork mode, not a local MCP chat.
Mode | Where it runs |
|
|
Regular Desktop chat | Your PC | Yes (if MCP connected) | Yes |
Cowork | Remote Linux VM | No | No |
Fix: In Claude Desktop, start a normal new chat (not Cowork). Cowork uses the pdf-translate skill in a VM; your MCP server only works in regular chat.
pdf-translate tools not listed
Quit Desktop fully (tray → Exit) after editing
claude_desktop_config.json.Reopen → new regular chat.
Check logs:
%APPDATA%\Claude\logs\formcp-server-pdf-translate.logor[pdf-translate]inmcp.log.If only
filesystemappears in logs, Desktop never startedpdf-translate— fix JSON syntax or Python path.
Server not listed
Connection error: Run
python server.pymanually — should hang waiting on stdin (that’s normal).ANTHROPIC_API_KEY: Must be in the
envblock of Desktop config.
4-minute timeout
Claude Desktop hard-kills any MCP tool call after ~4 minutes, even if the server is still working. Your 08:52 run proves this: the server was still translating when Desktop cancelled.
Use start_translate_pdf_job + get_translate_pdf_job for 50-page PDFs. The start call returns in under a second; poll until status is done.
If the MCP log shows asyncio.run() cannot be called from a running event loop, restart Claude Desktop after updating the server.
Large base64 fails
Use translate_pdf_path instead. Desktop caps tool payloads at ~1MB.
See PLAN.md for architecture notes.
This server cannot be deployed
Maintenance
Related MCP Connectors
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
Zotero MCP server for Claude and ChatGPT: search, citations, safe writes, PDF passages and pages.
MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceLocal MCP server that indexes folders of documents into a hybrid vector + keyword search index for Claude Desktop, with support for PDFs, Office files, and images via OCR.MIT
- AlicenseNot gradedqualityCmaintenanceA local MCP server for Claude Desktop with persistent task management, file operations, document generation, and PDF indexing.239 npm1MIT
- AlicenseAqualityDmaintenanceMCP server for translating PDFs using pdf2zh-next, preserving document context by extracting all text segments for LLM translation at once.53MIT
- FlicenseNot gradedqualityDmaintenanceMCP server enabling Claude Desktop to answer questions from local Word and PDF documents by searching a vector index built from their contents.-