Cold Open

io.github.TheYungStumpPublished by GitHub account TheYungStumpv0.1.0-alpha.3Updated Nov 7, 2026

Screenplay editing for agents: Fountain and .fdx; edits arrive as tracked changes in Cold Open.

VerifiedSTDIODesktop onlyFiles & StorageMedia & Design

Overview

AI-generated overview

MCP server for Cold Open, a screenwriting app, letting an assistant edit Fountain and Final Draft scripts as tracked changes.

What you can do
  • Open, read and edit screenplay documents, with blocks, pages and scenes exposed as resources
  • Insert blocks and replace text, with each edit appearing as a tracked change in the desktop app
  • List scenes and inspect document structure
  • Undo steps, with an agent able to undo only its own changes
  • Work on a script open in the desktop app, or open the file directly when the app is not running
When to use it
Useful when a writer wants an AI assistant to make or revise screenplay edits in Fountain or .fdx files while keeping visible, undoable tracked changes, rather than rewriting whole files.
Requirements
Runs locally as the coldopen mcp command, installed with the Cold Open desktop app (alpha builds for Windows, macOS and Linux) or built from source with Rust 1.89 or newer. No accounts, API keys or environment variables are declared. On Linux the app needs X11 or Wayland and libxkbcommon.
Before you install
Alpha software, and the builds are not yet signed or notarized, so first-start warnings appear. The agent can change and save script files; without a save the changes are discarded, but a batch with save writes to disk. An agent you connect is a separate program, so what it reads from your script and where it sends it is up to that program. If scripts are in a git repository, ignore the hidden journal files.

Installation

In SourceWeft

  1. Open Cold Open in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Cold Open

Cold Open is a free, open-source screenwriting app. It reads and writes Fountain and Final Draft (.fdx) files and never loses your work. Every action is a command, and you can drive it from the desktop app, the command line, JSON over stdio, or an MCP server.

Status: alpha, and looking for testers. Phases 1 to 5 built the editor, the command line, the MCP server, .fdx exchange, track changes, revisions, script diff and reports; phase 6a made the builds a writer installs, and 6b the user guide, feedback and crash reports. The website, https://theyungstump.github.io/cold-open/, has the user guide and how to join the alpha. See docs/spec.md for the plan, docs/progress/ for each phase and CHANGELOG.md for each release.

Install

Alpha builds for Windows (x64 and ARM64), macOS (Apple Silicon and Intel) and Linux (x86-64 and ARM64; .deb, AppImage and Flatpak) are on the releases page. Each download is under 15 MB. They aren't signed by Microsoft or notarized by Apple yet (see the code signing policy); the release notes say how to get past the first-start warning on each system. The command-line tool coldopen comes with the app on every system (docs/specs/release.md §4).

To help us measure Cold Open on your computer, choose Measure performance in the palette, or run coldopen bench, and send us the two small files it writes to your Downloads folder (docs/specs/bench.md). They hold model names and times, and nothing personal.

Code signing policy

Free code signing provided by SignPath.io, certificate by SignPath Foundation.

Cold Open is applying to SignPath Foundation's program for open-source projects. Until the project is accepted, the Windows builds are unsigned, and Windows warns about them the first time they run.

Team roles:

  • Authors (committers), who may change the source without another review: TheYungStump.
  • Reviewers, who review every change from anyone else, such as a pull request, before it is merged: TheYungStump.
  • Approvers, who approve each signing request by hand: TheYungStump.

How a release is signed:

  • Each release is built from source by GitHub Actions, from a tagged commit of this repository (.github/workflows/release.yml).
  • Only Cold Open's own programs are signed: the desktop app, the command-line tool and the Windows installer.
  • An approver approves each signing request by hand.
  • Every team member uses multi-factor authentication for GitHub and for SignPath.

Much of Cold Open's code is written with AI coding agents, working under the author's direction and GitHub account. The author reviews every change before it is merged.

Privacy

This program will not transfer any information to other networked systems unless specifically requested by the user or the person installing or operating it.

In short: the website counts visits anonymously with Cloudflare Web Analytics, without cookies; the app sends nothing.

In practice:

  • Cold Open makes no network connections. It doesn't check for updates or contact any server.
  • A usage summary, on your computer only (from 0.1.0-alpha.3). Cold Open counts which features you use, on this computer only, and it's never sent unless you include it in feedback. It holds counts, never your text, names or file paths. Settings (Ctrl+Comma, or Cmd+Comma on a Mac) shows it in full, resets it, or turns counting off. (docs/specs/usage-summary.md)
  • The agent link stays on your computer. The app and coldopen mcp talk through a socket or a pipe that only your user account can open (docs/specs/mcp.md). An AI agent you connect is a separate program: what it reads from your script, and where it sends it, is up to that program and its own privacy policy.
  • Links open in your browser, and only when you click them.
  • Measure performance writes two report files to your Downloads folder. They leave your computer only if you send them.

From 0.1.0-alpha.2, there are two ways to tell us about a problem from inside the app. Neither sends anything by itself:

  • Report a problem… opens a page in your browser, ready to fill in: a GitHub issue, or a Google Form for people without a GitHub account. The app fills in Cold Open's version and commit, the build's target, your operating system's name and version, and the renderer drawing the window. It adds no script text, no file names or paths, and no user or computer names. Nothing is sent until you submit the page yourself, and you can change it first.
  • Crash reports. If Cold Open crashes, it saves a report on your computer: the error's message with any quoted text taken out, where in Cold Open's code it happened, a backtrace as code addresses with no file paths, the version, the operating system and the renderer. It holds no script text, file names or user names. At the next start, Cold Open asks whether you want to look at it. It shows you the whole report before anything leaves your computer. Then it can open a ready-filled issue or form, or copy the report for you to paste. You can choose Never ask again.

The website counts visits anonymously with Cloudflare Web Analytics, without cookies, in aggregate; nothing else measures visitors (the site's privacy page).

GitHub issues are public, under GitHub's privacy statement. Form answers go privately to the project, through Google Forms, under Google's privacy policy.

Build

You need Rust 1.89 or newer. Install it from https://rustup.rs, then build:

bash
cargo build --release

This builds two programs in target/release: coldopen-app, the desktop app, and coldopen, the command-line tool, which also runs the MCP server. Both run on Windows, macOS and Linux (.exe on Windows). On Linux the app needs X11 or Wayland, and libxkbcommon, at run time.

Packages for every system are built by CI (.github/workflows/build.yml, .github/packaging/package.sh); every pull request's run has them under Summary ▸ Artifacts.

Use the desktop app

bash
coldopen-app [script.fountain]
  • Writing. A new script starts on a scene heading. Enter and Tab move between elements as screenwriting expects (heading, action, character, dialogue, parenthetical, transition); the bar at the top says what they will give next. Typing in headings, character names and transitions comes out in capitals. Autocomplete offers character names, INT./EXT., locations, times of day and extensions; Tab or Enter takes a suggestion.
  • Everything from the keyboard. Ctrl+K (Cmd+K on macOS) opens the command palette, which lists every command, every app action and their shortcuts, and recent files.
  • Pages. The script is shown on pages exactly as it prints, or in a continuous draft view (Ctrl+Shift+D). The navigator on the left lists scenes; drag one, or press Alt+Up/Down, to move it.
  • Files. Ctrl+S saves (in the background, without pausing your typing), Ctrl+Shift+E exports a PDF, and closing asks about unsaved changes.
  • Your own keys and element flow. keymap.json and flow.json in the settings folder change shortcuts and what Enter and Tab do; see docs/specs/editor.md §5.2 and §10. The app never rewrites them.
  • Drawing. The app draws with the CPU on Windows and Linux and with the GPU on macOS. The GPU is smoother on 4K and Retina screens; the CPU uses far less memory. The palette switches between them.

The full behaviour is in docs/specs/editor.md.

Let an AI agent edit your script

bash
claude mcp add coldopen -- coldopen mcp

coldopen mcp is an MCP server: every command is a tool (block_insert, text_replace, scene_list and so on), and the script, its blocks, pages and scenes are resources. Any MCP client works the same way.

When the script is open in the desktop app, the agent's doc_open attaches to the app instead of opening the file: you see each edit appear, a violet bar marks the blocks it changed, and Ctrl+Z undoes it like your own. Each agent step is labelled with the agent's name and the tool it used, and an agent can only undo its own steps. The status bar shows a connected agent, with Disconnect and a switch that turns agent access off.

The link between them is private to your user account on your machine: a socket in a folder only you can open, or a Windows pipe only you can reach, plus a fresh 256-bit token. Without the app, coldopen mcp opens the file itself, with the same crash journal. Details: docs/specs/mcp.md.

Use the command line

Convert a script

bash
coldopen convert draft.fountain clean.fountain

This rewrites a script as canonical Fountain. The meaning is unchanged; spacing and markup are tidied.

To print the document's blocks and ids as JSON instead:

bash
coldopen convert draft.fountain - --to json

Use - as the output to write to standard output. If the target format cannot hold everything in the script, nothing is written unless you add --allow-lossy.

List scenes

bash
coldopen scenes draft.fountain

The output looks like this:

   1  1    p. 1     3/8  EXT. LIGHTHOUSE - DUSK  (15 blocks, 39 words)   2  2    p. 1     2/8  INT. RADIO ROOM - NIGHT  (5 blocks, 18 words)

Each line shows the page the scene starts on and its length in eighths of a page. Add --json for machine-readable output.

Export a PDF

bash
coldopen export draft.fountain draft.pdfcoldopen export draft.fountain review.pdf --watermark "DRAFT" --scene-numbers

The PDF uses the bundled Courier Prime font and comes out byte for byte the same on Windows, macOS and Linux. --no-title-page leaves out the title page. Characters the font has no glyph for (for example Chinese or emoji) print as a box, and the command says which.

See the pages as text

bash
coldopen pages draft.fountain

prints every page the way it prints, as plain text on a 10-characters-per-inch grid, with a header line per page saying why it ended. It is handy for checking page breaks.

Licenses

coldopen licenses prints Cold Open's license and the SIL Open Font License of the bundled fonts. The app shows them under About in the palette.

Run a batch of edits

edits.json is a JSON array of commands, or one command per line:

json
[  {"command": "text.replace", "params": {"find": "MAYA", "with": "NINA"}},  {"command": "block.insert", "params": {"type": "transition", "text": "FADE OUT."}}]

Run it against a script:

bash
coldopen run edits.json --doc draft.fountain --save
  • run prints one JSON response per command.
  • It stops at the first failure unless you add --keep-going.
  • It exits with status 1 if any command failed.
  • Without --save (or a doc.save in the batch), changes are discarded when the batch ends.
  • Unsaved work recovered from a crash journal is never thrown away. If the batch leaves it untouched, it stays in the journal for the next open; if the batch changed it, a copy of the journal is kept, and run says where.

Serve commands over stdio

bash
coldopen serve --stdio

The server reads one JSON request per line and answers each with one JSON response line. Any language can drive it this way:

→ {"v":1,"id":1,"command":"doc.open","params":{"path":"draft.fountain"}}← {"v":1,"id":1,"ok":true,"result":{"blocks":42,"format":"fountain","path":"draft.fountain","recovered":null,"scenes":6,"warnings":[]}}→ {"v":1,"id":2,"command":"block.insert","params":{"after":"b_3","type":"character","text":"MAYA"}}← {"v":1,"id":2,"ok":true,"result":{"id":"b_43"}}→ {"v":1,"id":3,"command":"undo"}← {"v":1,"id":3,"ok":true,"result":{"undone":"block.insert"}}

The full command list, parameters and error codes are in docs/specs/commands.md.

Your work is safe

The crash journal. While a script is open, every change is written to a crash journal before the command returns. For draft.fountain, the journal is the hidden file .draft.fountain.coldopen-journal next to it.

  • If Cold Open crashes, or the machine loses power, the next doc.open replays the journal and returns "recovered": {"commands": N}. Your undo history comes back too. The desktop app shows what came back and lets you keep it or go back to the saved file.
  • In the desktop app, every key is written to the journal before it shows, and flushed to disk within 250 ms. Ending the app at any moment loses nothing that was on screen; a power cut loses at most the last quarter of a second. A script you never saved has a journal too, and the app offers it at the next start.
  • Saving resets the journal, and closing a saved document deletes it.
  • If the script is in a git repository, add .*.coldopen-journal to your .gitignore.

Atomic saves. Saves are atomic: a crash mid-save leaves the old file or the new one, never half of each.

The details are in docs/specs/journal.md.

Fountain support

Cold Open supports everything on the Fountain syntax page:

  • the title page
  • scene headings, including forced headings and scene numbers, plus the reversed EXT/INT and E/I prefixes that some writers use
  • action, characters, dialogue, parentheticals and dual dialogue
  • lyrics, transitions and centered text
  • emphasis
  • notes, boneyard, sections and synopses
  • page breaks

Every rule, and how we settle the cases the syntax page leaves open, is written down in docs/specs/fountain.md.

Test

bash
cargo fmt --all --checkcargo clippy --workspace --all-targets -- -D warningscargo test --workspace

The test suite includes:

  • Fountain conformance cases. One case per rule, in tests/fixtures/fountain, with expected results written by hand.
  • Property tests. Random Fountain and random edit sequences check round trips, undo, redo and journal replay.
  • A crash test. It kills coldopen serve --stdio in the middle of a stream of edits, then checks that a new process recovers every edit that had been acknowledged.
  • The app's gates. The app's own tests run it headless, with real key presses through the real interface. The typing gate types a short scene with smart flow, autocomplete, accents, an undo and a save, and compares the file byte for byte; the crash gate kills the app as a separate process at random points mid-typing and checks the recovery; the agent gate drives a real coldopen mcp process against the app.

Private corpus

Real scripts are copyrighted, so they are never committed. Put any .fountain files under corpus/ (which is gitignored), or point COLDOPEN_CORPUS at another folder. The corpus test then checks that each script round-trips without loss. Without a corpus, that test is skipped.

Fuzzing

The fuzz/ folder holds cargo-fuzz targets. They need nightly Rust and run on Linux or macOS:

bash
cd fuzzcargo +nightly fuzz run fountain_roundtrip

The other targets are envelope, journal_replay, fdx_read, link_line and app_config. A scheduled workflow runs all six every Sunday; you can also start it by hand from the Actions tab.

Layout

CrateLicenseWhat it holds
crates/screenplayMIT OR Apache-2.0Screenplay types: elements, rich text, title page
crates/fountainMIT OR Apache-2.0The Fountain parser and writer
crates/fontsOFL-1.1 (fonts), MIT OR Apache-2.0 (code)The bundled fonts: Courier Prime for the page, Atkinson Hyperlegible Next for the app's interface
crates/layoutMIT OR Apache-2.0Layout on a character grid, pagination, page view and PDF export
crates/fdxMIT OR Apache-2.0A read-only .fdx reader (phase 2); writing and repair come in phase 4
crates/coreGPL-3.0-or-laterDocument, commands, dispatcher, undo, journal, atomic save
crates/cliGPL-3.0-or-laterThe coldopen binary
crates/appGPL-3.0-or-laterThe desktop app, coldopen-app
crates/mcpGPL-3.0-or-laterThe MCP server behind coldopen mcp
crates/linkGPL-3.0-or-laterThe private link between the app and coldopen mcp

The format libraries are permissively licensed so other apps can use them. The app itself is GPL-3.0-or-later; see LICENSE. The Courier Prime and Atkinson Hyperlegible Next fonts are under the SIL Open Font License 1.1 (crates/fonts/fonts/); PDFs you export are yours and are not covered by it.

tools/refpdf is a development tool that measures reference PDFs for the layout tests; it is never shipped.

Source: README.md at commit 4de7b2f

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0-alpha.3LatestNov 7, 2026

Score

50% 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 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • 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