Allows fetching Craig recordings from Discord and processing them into per-speaker tracks for transcription, using Discord IDs to label speakers.
Commits generated session documents (transcript, recap, combat report, GM notes, and party snapshot) to the campaign repository.
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., "@scribe process the session for tonight"
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.
An app that turns a night at a D&D 5e Foundry VTT table into its session record. It reads four inputs: the Craig recording from Discord, the Foundry chat log, Battle Flow's combat stats and the party's sheets. From them it writes a speaker-labelled transcript, a player recap (email and PDF), a combat report, GM notes and a party snapshot into your campaign repo.
Claude Code drives it. The app runs as an
MCP server named scribe, and its session-scribe skill runs
the pipeline.
It reads the world and never writes it. The session-diary page goes in through the sibling
fvtt-mcp-dnd5e.
At the table, the DM does four things: /join Craig, play, /stop, and paste the link to
Claude. There is nothing to mark, export or download. A "mark that" said aloud is found in the
transcript.
git clone https://github.com/Txpple/fvtt-app-sessionscribe && cd fvtt-app-sessionscribe
npm install && npm run build # fvtt-mcp-dnd5e must be cloned beside this repo and built first
cp .env.example .env # FOUNDRY_SCRIBE_USER / FOUNDRY_SCRIBE_PASSWORD, SCRIBE_CAMPAIGN_REPO
claude mcp add -s user scribe -e FOUNDRY_HOST=molten -- node /absolute/path/to/fvtt-app-sessionscribe/dist/index.jsThen, once per machine:
Transcription toolchain. Run powershell -ExecutionPolicy Bypass -File scripts\setup.ps1 -PrefetchModel.
It installs ffmpeg, builds a Python venv with faster-whisper and the CUDA wheels, and runs a
smoke test. It is idempotent.
The skill, in every project. From the repo root in PowerShell, run
New-Item -ItemType Junction -Path "$HOME\.claude\skills\session-scribe" -Target "$PWD\.claude\skills\session-scribe".
The scribe's own Foundry user. Create an Assistant GM user (default Scribe Assistant).
Don't reuse the MCP's user: two clients on one user double Battle Flow's automation.
Restart Claude Code and ask for scribe-status, which reports anything missing.
FOUNDRY_HOST is molten or local. It sets the default host for reads, and each read tool
can override it per call. The host URLs come from fvtt-mcp-dnd5e's .env, not this repo's.
Requirements:
Windows and Node.js 22+.
fvtt-mcp-dnd5e, built, beside this repo.
Microsoft Edge, for the PDFs.
An NVIDIA GPU for transcription. The CPU works, but slower.
A dnd5e world. Battle Flow is needed only for the combat report.
The Craig bot in your Discord server.
A campaign repo: campaign.json + STYLE.md, as described in
campaign-repo.md.
Related MCP server: Scribe MCP
Paste a Craig link, or say "process the session". The session-scribe skill runs the
pipeline in this order:
Check, fetch and transcribe.
Export the chat log, build the transcript and analyse the combat.
Write the recap, the combat log and the GM notes.
Render the PDFs and look at every page.
Snapshot the party and add the session-diary page.
Commit to the campaign repo.
The tools handle correctness and the skill handles judgment: the recap's voice, which beats
matter, and the illustrations, which it makes with
fvtt-app-artificer's illustration-builder.
Tool | Does |
| checks health (Python + CUDA, ffmpeg, Edge, the campaign repo, the login; |
| turns the Craig link (or the DM's own flac zip) into one track per speaker, labelled by Discord id. Runs as a job |
| runs faster-whisper on each track → |
| exports the recording window's chat log → |
| merges speech and chat by wall clock → |
| turns Battle Flow's stat stamps into per-combat damage, accuracy, healing, spends and moments |
| exports the party's sheets in full (restorable with Import Data), plus the digest facts |
| prints the outputs' HTML to PDF with headless Edge, and saves every page as a JPEG to check |
The record goes into the campaign repo, under sessions/YYYY-MM-DD/ and party-snapshots/.
campaign.json's sessions.outputs picks which documents a session gets.
The spoiler boundary is a file.
transcript-public.md withholds every whisper and blind roll. The player recap and the
session-diary page are written from it alone.
transcript.md, where whispers are marked 🤫, feeds only the GM's documents.
The audio, the job logs and the page previews stay in the session's audio/, which is
gitignored. The Craig key is never saved.
Joining Foundry. Each Foundry read runs in its own child process through fvtt-mcp-dnd5e's
headless-Chromium client, joined as the scribe's user. It refuses to read in three cases:
another world, a login below Assistant GM, or the scribe being the elected GM while a combat
runs.
Long steps. Fetching and transcribing are detached jobs that log to the session's
audio/.jobs/, so they never block the server.
Timing. Speech and chat are aligned by wall clock: Craig's startTime against Foundry's
epoch-ms timestamps. There are no markers and no sync step.
The offline gate is npm run check && npm run typecheck && npm test && npm run build && npm run knip.
The tests run on fakes, never on live APIs. node scripts/call.mjs <tool> '<json>' runs one tool
through a fresh dist/index.js.
The live checks run on a sandbox only:
FOUNDRY_HOST=local node scripts/verify-reader.mjs proves that the reader leaves no trace.
parity-chat.mjs and parity-snapshot.mjs compare the output with the MCP's exporters.
MIT — see LICENSE.
This server cannot be deployed
Campaign manager for D&D and TTRPG GMs: your AI reads and writes a live typed campaign database.
Transcribe recordings into a speaker-labelled transcript with timestamps and a summary.
Connect any AI to your Foundry VTT world: actors, combat, dice, journals, tokens, compendiums.
Manage your tabletop RPG campaign from any MCP client: worlds, sessions, quests, lore, recaps.
