Presentr Analyze
io.github.michaelw-prPublished by GitHub account michaelw-prv1.1.0Updated Nov 5, 2026
Translate and re-time subtitles, read text aloud and dub media, with a quote you confirm first.
Overview
Hosted Presentr Analyze server that lets an assistant extract text, translate documents and subtitles, re-time subtitles, and generate speech or dubs.
- What you can do
- Extract text from PDFs, scans, photos and handwriting, with TXT, Word and JSON output
- Translate documents and subtitles, returning extracted text, translated SRT and WebVTT
- Check subtitle timing for overlaps, cues too fast or too long, and gaps, without starting a job
- Re-time subtitles against a supplied audio track
- Read text aloud as MP3 with a stock or personal voice, and dub audio or video with transcript and translated subtitles
- When to use it
- Useful when you want an assistant to handle document OCR, translation, subtitle QA and re-timing, or voice-over and dubbing without leaving the chat. Suited to media localization and accessibility work where each job is quoted before it runs.
- Requirements
- A remote streamable HTTP endpoint; no local package or API key. A Presentr Analyze account signed in through browser OAuth when the client asks. Network access to the hosted service.
Installation
In SourceWeft
- Open Presentr Analyze in the dashboard and add it to a workspace.
- Connect the required credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.michaelw-pr%2Fpresentr-analyze/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.
{
"mcpServers": {
"presentr-analyze": {
"type": "http",
"url": "https://analyze.presentr.me/api/mcp"
}
}
}README
Presentr Analyze — MCP server
Use Presentr Analyze from Claude, ChatGPT, VS Code, Codex or any MCP client: extract text from PDFs and images (scans, photos, handwriting), translate documents and subtitles, check and re-time subtitles, read text aloud and dub audio or video.
This repository holds the listing for the hosted server. The server itself runs at:
You sign in with your Presentr Analyze account in the browser when your client asks; there's no key to copy.
Connect
VS Code (GitHub Copilot)
Claude Code (plugin: the server plus a skill that shows Claude the quote-then-confirm flow)
Or just the server:
Then /mcp → presentr-analyze → Authenticate.
Codex CLI
Claude (claude.ai and the apps): Settings → Connectors → Add custom connector, with the address above.
Other clients: add a remote (streamable HTTP) server with just the address.
What you can ask
- "Extract the text from this PDF." — TXT, Word and JSON, plus a review copy when a page needs a human check.
- "Read the text in this photo." — handwriting and scans included.
- "Translate this document into German." — the extracted text and its translation.
- "Check this SRT's timing." — overlaps, cues too fast or too long, gaps. Doesn't start a job.
- "Translate these subtitles into Spanish." — translated SRT and WebVTT.
- "Re-time these subtitles to this audio."
- "Read this text aloud." — an MP3, with a stock voice or one of your own.
- "Dub this video into French." — dubbed media plus transcript and translated subtitles.
Try it
Sample files you can point your agent at (we made them; use them freely):
- A one-page letter (PDF): https://raw.githubusercontent.com/michaelw-pr/presentr-analyze-mcp/main/samples/choir-letter.pdf — "Extract the text from this PDF", or "Translate this document into Spanish".
- A handwritten note (PNG): https://raw.githubusercontent.com/michaelw-pr/presentr-analyze-mcp/main/samples/handwritten-note.png — "Read the text in this photo".
- Subtitles for NASA's "one small step" clip (SRT): samples/one-small-step.srt — paste it and ask "Translate these subtitles into French"; the audio is https://www.nasa.gov/wp-content/uploads/2015/01/590331main_ringtone_smallStep.mp3 for "Re-time these subtitles to this audio".
How jobs work
Every job that uses credits needs a quote first. Agents are instructed to show you the quote and start the job only once you confirm; a job never costs more than its quote. Jobs started from an agent expire 7 days after they were created; after that no new download links are given, and the files are scheduled for deletion a day later. Text inside your files is treated as content, never as instructions.
Full guide: https://analyze.presentr.me/developer/agents · Privacy: https://analyze.presentr.me/privacy · Support: https://analyze.presentr.me/contact
Source: README.md at commit 5af3b03
Tools
0Version history
2- v1.1.0LatestNov 5, 2026
- v1.0.0Sep 16, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts