Alto Connector
Integrates with Firebase for publishing Alto timelines as shareable web pages and enabling cross-device synchronization of highlights, notes, and reports. Users host their own Firebase project to control access and data.
Click on "Install 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., "@Alto ConnectorI want to build a timeline in Alto — interview me."
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.
Alto Connector
mcp-name: io.github.lukebmandel-debug/alto-connector
A Claude connector that interviews you about your own materials — a course, a novel, a research project — and builds you an interactive, filterable "liquid-glass" Alto timeline: glass cards on colored act bands, entity chips, routed connection lines, detail pages with your own schema, highlights and notes, mobile layout, and a self-contained offline file you can share.
The one rule (§0): Alto is a closed knowledge container. It connects and organizes what you provide — it never invents facts, events, holdings, or descriptions. Sparse notes make a sparse timeline, on purpose. The connector enforces this server-side: authoring tools stay locked until your materials and explicit consent are recorded.
Install
Download the file for your computer from the latest release, then in Claude Desktop go to Settings → Extensions → Advanced settings → Install Extension… and choose it. Restart Claude Desktop and Alto appears under Extensions.
macOS, Apple Silicon |
|
macOS, Intel |
|
Windows, 64-bit |
|
Nothing else to install. Each bundle carries its own Python, which is why it is around 50MB. Claude Desktop ships Node but not Python, and stock macOS still has 3.9 — too old for this server.
Without Claude Desktop
Alto is a plain MCP server, so any MCP client can run it — Claude Code, Cline, Zed, Continue, your own script. No download, no bundle.
Add this to your client's MCP config:
{
"mcpServers": {
"alto": {
"command": "uvx",
"args": ["--from",
"git+https://github.com/lukebmandel-debug/alto-connector",
"alto-connector"]
}
}
}Requires uv
(curl -LsSf https://astral.sh/uv/install.sh | sh). uvx fetches and runs
Alto in a throwaway environment each time, so there is nothing to install or
update.
Prefer a permanent install? Then alto-connector is on your PATH and the
config is simply {"command": "alto-connector"}:
pip install git+https://github.com/lukebmandel-debug/alto-connector
alto-connector --help # check it works; without --help it waits for a
# client to speak to it, which looks like a hangEverything works the same way — the interview, the build, the offline file — because the bundle and this are the same server; the bundle just carries its own Python so Claude Desktop users need not install one.
Timelines land in ~/Documents/Alto. Each is a single self-contained HTML
file you open in any browser — no server, no account, no internet. Shareable
web links are optional (see Publishing below); without them, that file is the
finished product.
Then tell your client: "I want to build a timeline in Alto — interview me."
From a checkout
bash setup.sh — macOS and Claude Desktop only; it registers the
connector by writing claude_desktop_config.json. For any other client, use
one of the two methods above pointed at your checkout.
Related MCP server: Rhylthyme MCP Server
Using it — what a new user actually does
Open a chat and say something like "I want to build a timeline in Alto — interview me."
Claude calls
get_interview_guideand runs a short warm interview:Flow 1 — name the project container and what it's for.
Flow 2 §A — the materials gate: you hand over your actual materials (upload files or paste text into the chat), and explicitly agree that Alto builds only from them.
§B–§I — title, what the axis means, your acts/eras, your entities (characters, doctrines, teams…), node schema (e.g. Facts·Issue·Holding· Rule for law), relationship vocabulary for the lines, extra filter axes, persona, presentation.
Claude authors nodes verbatim from your materials, wires connections, runs a layout preview, builds (a verifier gates every build), and publishes.
You get your timeline two ways:
Offline file (always): one self-contained HTML — double-click to open, send to a friend, works forever with no server.
Web links (optional, still free): if Firebase publishing is configured,
https://<your-site>.web.app/t/<timeline>/plus a homepage listing all your published timelines, a reports page, and cross-device sync of highlights/notes/reports.
Come back any time — drafts resume across chats via
get_timeline.
Publishing (optional web links + cross-device sync)
Timelines are private by default and the offline file always works. To publish shareable links — and to get highlights, notes and reports syncing between your desktop and your phone — you host them on your own free Firebase project (Spark plan, no card).
You host what you share. Everyone who authors a timeline publishes to their
own project, so the people you send a link to read it from your site and their
notes live in your Firestore. That means you can revoke a link at any time
(publish_timeline(timeline_id, visibility="private") deletes the page from
your site), and it means nobody's data flows through anyone else's project.
Reading a shared timeline needs no install and no Alto account — just the link.
console.firebase.google.com → create a project → Hosting → add a site (e.g.
my-alto).Enable Firestore and Authentication → Google in that project, and deploy the per-user rules in
firestore.rules(firebase deploy --only firestore:rules). Do this before publishing: a Firestore left in test mode is world-readable and world-writable for 30 days.npm i -g firebase-tools && firebase loginOpen Alto's settings in Claude Desktop (Settings → Extensions → Alto) and fill in Firebase Hosting site, Firebase project id and Firebase web config. From a checkout instead, set
ALTO_FIREBASE_SITE,ALTO_FIREBASE_PROJECTandALTO_FIREBASE_CONFIGin the environment.The web config comes from Firebase console → Project settings → Your apps → SDK setup and configuration. It is spliced into
alto-cloud.jsat publish time. Leave it unset and sync is simply off: highlights stay in the browser's local storage on each device.ALTO_FIREBASE_BINoverrides the path to thefirebaseCLI if it is not on yourPATH.
Two things worth knowing before you share a link. Published means public to anyone who has the URL — the address carries a random tail so it cannot be guessed, but it is not access-controlled. And a reader who signs in to sync their notes gets an account in your Firebase project: the security rules stop you reading their notes through the app, but you own the project and can see them in the Firebase console.
Repo layout
engine/— the three page templates, extracted content-free from the reference build. The extraction fixtures they were derived from are not published: they contain the author's own writing.test_roundtrip.pyskips without them.alto/build/— brief model, height estimator, layout resolver (a port of the engine's own), block generators, verifier, offline bundler.alto/mcp_server.py— the 14 MCP tools + interview prompt.alto/build/sanitize.py— makes user content inert before it reaches a page. Load-bearing: the engine renders detail sections straight intoinnerHTML.alto/publish_static.py— free-tier static publishing via the Firebase CLI.packaging/— the .mcpb bundles, the download page and the registry entry. Seepackaging/README.md.alto/web.py,alto/auth/— a full remote-server variant (streamable HTTPOAuth 2.1), not used by the local install; kept for a future hosted deployment.
Development
.venv/bin/python -m pytest tests/ # incl. the golden round-trip
python3 -m alto.build samples/contracts_brief.json --bundle # CLI buildPrivacy
See alto/privacy.html. Short version: your source documents stay in your
Claude conversation; the connector stores only what it builds, locally in
~/Documents/Alto (and, if you publish, on your own Firebase site).
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseBqualityDmaintenanceEnables managing personal information with dynamic topic-based organization (tasks, meetings, contacts, etc.), supporting optional OTP authentication and AES-256 encryption for sensitive data with automatic backups.Last updated106
- Alicense-qualityCmaintenanceEnables the creation of interactive schedule visualizations on rhylthyme.com featuring parallel tracks, dependencies, and resource constraints. Users can import recipes or protocols from external sources and define custom workspace environments to generate shareable timelines with live execution timers.Last updatedMIT
- Alicense-qualityDmaintenanceProvides Claude with persistent local memory and a structured knowledge graph for tracking project states, task dependencies, and historical context. It enables users to store notes, manage task relationships, and perform time-travel queries to reconstruct past information without relying on cloud services.Last updatedMIT
- AlicenseAqualityBmaintenanceCaptures ideas from conversations and organizes them into a persistent, hierarchical mindmap. Supports search, deduplication, export, import, and cloud sync.Last updated138MIT
Related MCP Connectors
Build personal interactive apps with real URLs and persistent storage, using any AI.
Make videos and docs with your AI agent — describe what you need, every output stays editable.
Source-first URL clone, capture, rebuild, and fidelity verification tools.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/lukebmandel-debug/alto-connector'
If you have feedback or need assistance with the MCP directory API, please join our Discord server