Turns one TypeScript file into CLI tools, MCP servers, and web interfaces that AI clients and humans can invoke.
Also known as portel-dev/photon, @portel/photon
- Stars
- 100
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Oct 19, 2026
- License
- MIT
What is Photon MCP?
Photon turns one TypeScript file into CLI tools, MCP servers, and web interfaces that AI clients and humans can invoke.
Summary generated from the project's README
About Photon MCP server
Developers can transform a single TypeScript file into a complete suite of interfaces including CLI tools, MCP servers, and web interfaces. By writing a single TypeScript class with specific method signatures and JSDoc comments, you automatically generate the necessary contracts for both human users and AI agents. This allows a single piece of logic to serve as a command-line utility, a web dashboard called Beam, and a tool for AI clients like Claude, ChatGPT, or Cursor.
Setting up a local MCP server is done through the command line using photon mcp install. The system supports local stdio connections for Claude Desktop and public HTTPS endpoints for ChatGPT developer mode. It requires Node.js 20 or higher and handles all TypeScript compilation internally without needing a separate configuration file. This approach ensures that the same validation rules, documentation, and types are applied consistently across every surface, whether an agent is invoking a tool or a human is using the auto-generated web form.
What you can do with it
- 1Deploying an MCP serverRegister a TypeScript capability as a tool within Claude Desktop or other MCP-compatible clients.
- 2Generating human-readable interfacesCreate an interactive web dashboard for manual tool testing and data entry without writing frontend code.
- 3Automating tasks via CLIExecute specific TypeScript methods directly from a terminal for scripts and automation.
- 4Building production workflowsExpand a simple method into a complex system with webhooks, schedules, and audit history.
Written from the project's README. Every use case is checked against a quote from it.
How to install Photon MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Photon MCP in Claude Code
$ claude mcp add photon -- npx -y @portel/photonInstall Photon MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"photon": {
"command": "npx",
"args": [
"-y",
"@portel/photon"
]
}
}
}Install Photon MCP in VS Code
.vscode/mcp.json
{
"servers": {
"photon": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@portel/photon"
]
}
}
}Install Photon MCP in VS Code CLI
$ code --add-mcp '{"name":"photon","type":"stdio","command":"npx","args":["-y","@portel/photon"]}'Install Photon MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"photon": {
"command": "npx",
"args": [
"-y",
"@portel/photon"
]
}
}
}Install Photon MCP in Codex
$ codex mcp add photon -- npx -y @portel/photonInstall Photon MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.photon] command = "npx" args = ["-y", "@portel/photon"]
Install Photon MCP in Gemini CLI
$ gemini mcp add -s user photon npx -- -y @portel/photonInstall Photon MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"photon": {
"command": "npx",
"args": [
"-y",
"@portel/photon"
]
}
}
}Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubOne TypeScript capability becomes the whole agent stack.
Photon is the fastest way to turn a small, verified TypeScript method into something humans can operate and agents can trust. Write the capability once; Photon derives the interfaces, contracts, and runtime behavior around it:
- MCP server for Claude, ChatGPT, Cursor, and agents
- Embedded app UI for chat clients that support MCP app resources
- CLI tool for scripts, demos, and automation
- Beam web interface for humans
- Web routes, schedules, webhooks, retries, state, and audit history when the capability grows into a production workflow
Photon is free and open source software released under the MIT license. Full documentation lives at photon.portel.dev.
Related Portel project: NCP gives agents one natural MCP interface to discover and run tools across a whole tool ecosystem. Photon builds reliable agent-facing capabilities; NCP helps agents find and use them alongside every other MCP.
Try it in two minutes:
bun add -g @portel/photon
photon new my-tool
photon
That opens Beam, the generated human UI. Add photon mcp install my-tool when
you want the same capability inside Claude Desktop or another MCP client.
Interfaces are optional. Intent is mandatory.
gh repo star portel-dev/photon
From one method to every surface
The weather example is intentionally small: one TypeScript method, a few
docblock tags, and one @ui HTML asset. Photon turns that into a CLI command,
Beam UI, MCP tool, and embedded app surface for MCP app-capable chat clients.
Claude Desktop can run it from a local stdio MCP command; ChatGPT developer
mode can connect to the same Photon over a public HTTPS /mcp endpoint.
Real clients, same Photon:
Follow the step-by-step tutorial
or open the runnable example in
examples/weather-showcase.
The tutorial also includes Beam, CLI, and a concept animation for the full
transformation.
The Photon Promise
Photon is the modern dev stack for the agentic age: each photon is a small, auditable brick that can be used by humans, agents, schedulers, webhooks, and apps without rewriting the same capability for every interface.
That is the core idea: tiny trusted capabilities compose into larger systems. A photon can start as a helper method, become a CLI command, render as an app, run on a schedule, accept webhooks, and still expose a clean agent-readable contract.
Example
// hello.photon.ts
export default class Hello {
greet(name: string) {
return `Hello, ${name}!`;
}
}
That's a complete photon. From this single file you get:
$ photon cli hello greet --name Ada # CLI
$ photon # Web UI at localhost:3008
$ photon mcp hello # MCP server for Claude, Cursor, etc.
No decorators. No registration. No server boilerplate. Just define the intent. Photon handles the rest.
Quick Start
From zero to an MCP server connected to Claude Desktop in three commands:
bun add -g @portel/photon
photon new my-tool # Scaffolds ./my-tool.photon.ts in your CWD
photon mcp install my-tool # Registers it in Claude Desktop's config
# Restart Claude Desktop. Your tool is live.
Prefer the web dashboard? Skip step 3 and run photon instead — it opens Beam, the auto-generated UI.
Or try without installing globally:
bunx @portel/photon new my-tool
bunx @portel/photon mcp install my-tool
# pnpm users can use pnpm dlx instead:
pnpm dlx @portel/photon new my-tool
pnpm dlx @portel/photon mcp install my-tool
Requires Node.js 20+. TypeScript is compiled internally; no
tsconfig.jsonneeded.Where do photon files live?
./(a project directory you cd into) or~/.photon/(global, auto-discovered). User settings persist under~/.photon/state/<photon>/. See Where things live.
How It Works
You write a TypeScript class. Methods are your capabilities. Types describe what's valid. Comments explain the intent. Photon reads all of it and generates three interfaces from one file. Same logic. Same validation. Same data.
analytics.photon.ts → Beam · Web app · Webhook · WebSocket · CLI · MCP
The more you express, the more Photon derives:
| What you write | What Photon derives |
|---|---|
| Method signatures | Tool definitions: names, inputs, outputs |
| Type annotations | Input validation rules, UI field types |
| JSDoc comments | Documentation for AI clients and human users |
| Constructor parameters | Config UI, environment variable mapping, runtime injection (Photon, Cloudflare, CloudflareEnv) |
@tags |
Validation, formatting, scheduling, webhooks, and HTTP routes |
When you add a @param city {@pattern ^[a-zA-Z\s]+$} annotation, Beam validates it in the form, the CLI validates it before running, and the MCP schema enforces it for the AI. One annotation. Three consumers.
Three ways to author
extends Photon is one shape. You can also inject Photon as a constructor parameter when you already extend something else, or compose without inheritance — same API either way. CF resources reach the photon through a separate Cloudflare injection so portable photons stay portable. See docs/guides/PHOTON-INJECTION.md.
Reuse a Photon in application code
Existing Photons can also be application dependencies. Load their source through the public API and call methods from your own Node code:
import { createPhotonRuntime } from '@portel/photon';
const runtime = createPhotonRuntime();
try {
const todo = await runtime.photon<{
add(text: string): Promise<unknown>;
}>('./todo.photon.ts', { baseDir: '/srv/my-app/photons' });
await todo.add('Review the release');
} finally {
await runtime.close();
}
This manages initialization and shutdown without starting a server. It executes trusted code in your application process; the host owns authorization. The object is separate from a live Beam/daemon instance. Use MCP when your application needs to operate on that same live instance. For source resolution, persistence, and constructor-dependency lifecycle limits, see Photon as a library.
Beam: Human Exploration
Run the shared task-board walkthrough to see a human and an MCP client operate the same state.
Beam is the web dashboard. Every photon becomes an interactive form automatically. Run photon. That's the whole command.
The UI is fully auto-generated from your method signatures: field types, validation, defaults, layouts. You never write frontend code. When you add a {@choice a,b,c} tag to a parameter, Beam renders a dropdown. When you mark a string as {@format email}, the field validates email format. The UI evolves as your code does.
When forms aren't the right interface for what you're building, you can replace Beam's auto-generated view with your own HTML. A global named after your photon is auto-injected (e.g., analytics.onResult(data => ...)) — no framework required. window.photon.url is also injected and resolves to the Beam base URL so your HTML can construct fetch paths correctly whether running locally or behind a reverse proxy.
Custom UIs follow the official MCP Apps Extension and work across compatible hosts. See the Custom UI Guide.
Photons that declare HTTP routes with @get, @post, @put, @patch, or @delete are shown in Beam as web apps. Routes support dynamic path segments (e.g. @get /items/:id) matched by specificity: literal segments win over parameters. Beam proxies requests to those routes and injects an x-photon-base-path header so the app can construct correct absolute paths regardless of where Beam is hosted. Web apps and WebSockets are Photon application targets; MCP Apps are a separate official MCP extension for embedded UI resources.
AI Agents: Machine Invocation
Photon ships separate, tested MCP adapters: sessionful MCP 2025 over stdio and
Streamable HTTP, plus stateless MCP 2026-07-28 release-candidate support over
Streamable HTTP. See the
compatibility matrix and runnable clients,
or run photon doctor mcp against your installed runtime.
photon info analytics --mcp
{
"mcpServers": {
"analytics": {
"command": "photon",
"args": ["mcp", "analytics"]
}
}
}
Paste into your AI client's config. Your photon is now an MCP server. Claude can call your methods. Cursor can call your methods. Any MCP-compatible host can call your methods.
The AI sees the same thing a human sees in Beam: the method names, the parameter descriptions from your JSDoc, the validation rules from your types. The JSDoc comment you wrote to document the tool for yourself is what Claude reads to decide when and how to call it.
The MCP tools themselves work with Claude Desktop, Claude Code, Cursor, and any MCP-compatible client. When your photon has a custom UI, clients that support the MCP Apps Extension can render it natively, as shown in the weather proof above.
How a Photon Evolves
Here is how a photon grows. Each step adds one thing and gets multiple capabilities from it.
Add comments: AI understands your intent
/**
* Weather - Check weather forecasts worldwide
*/
export default class Weather {
/**
* Get the weather forecast for a city
* @param city City name (e.g., "London")
*/
async forecast(params: { city: string }) { ... }
}
The class description becomes how AI clients introduce the tool to users. The @param description is what the AI reads before deciding what value to pass. Same comments. Human help text and AI contract at once.
Declare configuration: a settings tool appears
export default class Weather {
/** User-tunable knobs. Photon auto-generates a `settings` tool from this. */
protected settings = {
/** Units for forecast values */
units: 'metric',
/** Polling interval in seconds */
pollIntervalSec: 300,
};
async forecast(params: { city: string }) {
const res = await fetch(`...?units=${this.settings.units}`);
return await res.json();
}
}
protected settings is the canonical way to expose runtime knobs. Photon reads the JSDoc on each property, generates an MCP settings tool with typed inputs, and persists user changes to ~/.photon/state/<photon>/<instance>-settings.json. Inside methods, this.settings is a read-only Proxy. To change a value, the user (or AI) calls the auto-generated settings tool.
For secrets that should never be persisted in a settings file (API keys, tokens), use a constructor parameter instead. Photon maps the parameter name to an env var:
export default class Weather {
constructor(private apiKey: string) {} // → WEATHER_API_KEY
}
The constructor pattern is for primitives that come from .env. The protected settings pattern is for everything else, including any knob the user should be able to change at runtime without restarting. When in doubt, reach for settings.
Add tags: behavior extends across all surfaces
/**
* @dependencies node-fetch@^3.0.0
*/
export default class Weather {
/**
* @param city City name {@example London} {@pattern ^[a-zA-Z\s]+$}
* @param days Number of days {@min 1} {@max 7}
* @format table
*/
async forecast(params: { city: string; days?: number }) { ... }
}
@dependencies installs node-fetch automatically on first run, no manual package install needed. The {@pattern} validates in the form, the CLI, and the MCP schema simultaneously. days becomes a number spinner with bounds. @format table renders the result as a table in Beam. One annotation, three surfaces.
System CLI dependencies
If your photon wraps a command-line tool, declare it and Photon enforces it at load time:
/**
* @cli ffmpeg - https://ffmpeg.org/download.html
*/
export default class VideoProcessor {
async convert({ input, format }: { input: string; format: string }) {
// ffmpeg is guaranteed to exist when this runs
}
}
What Comes for Free
Things you don't build because Photon handles them:
| Auto-UI | Forms, field types, validation, layouts generated from your signatures |
| Stateful instances | Multiple named instances of the same photon, each with isolated state |
| Persistent memory | this.memory gives your photon per-instance key-value storage, no database needed |
| Scheduled execution | @scheduled runs any method on a cron schedule |
| Webhooks | @webhook exposes any method as an HTTP endpoint |
| OAuth (client) | Built-in OAuth 2.0 flows for Google, GitHub, Microsoft |
| OAuth Authorization Server | Issue tokens to MCP clients yourself: CIMD + DCR, PKCE, OIDC id_token, RFC 8693 token exchange |
| SQLite persistence | Audit log, execution history, and OAuth grants survive daemon restart (bun:sqlite or better-sqlite3) |
| Daemon ops | photon ps lists and controls scheduled jobs, webhooks, and live sessions |
| Distributed locks | @locked serializes access: one caller at a time, across processes |
| Cross-photon calls | this.call() invokes another photon's methods |
| Cloudflare runtime | this.cf.r2('blobs'), this.cf.d1('app'), this.cf.kv('cache') — same shape locally (miniflare) and deployed (real bindings). See CF-BINDINGS.md |
| Real-time events | this.emit() fires named events to the browser UI with zero wiring |
| Live rendering | this.render() pushes formatted output to CLI and Beam in real time |
| Delegated LLM | this.sample() asks the driving agent's model to generate text — no API key, agent pays |
| Inline confirm / input | this.confirm() and this.elicit() route through the client's native UI (Beam dialog, Claude prompt) |
| Scoped remote access | photon claim generates a short-lived code to scope a remote MCP session to one directory |
| Standalone binaries | photon build compiles any photon to a single executable via Bun |
| Dependency management | @dependencies auto-installs npm packages on first run |
Coordination: Locks + Events
Two primitives. Together they unlock a class of things that are surprisingly hard to build today.
Locks serialize access. When a method is marked @locked, only one caller can execute at a time, whether that caller is a human in Beam, a CLI script, or an AI agent. Everyone else waits their turn.
Events push state changes to any browser UI in real time. this.emit({ event: 'boardUpdated', data: board }) on the server becomes chess.onBoardUpdated(handler) in your custom UI — named after your photon file. No WebSockets to configure. No polling. Events are delivered via SSE through the MCP Streamable HTTP transport.
Together: turn-based coordination with live state.
export default class Chess {
/** Make a move. Locks ensure human and AI alternate turns. */
/** @locked */
async move(params: { from: string; to: string }) {
const result = await this.applyMove(params.from, params.to);
// Browser UI updates instantly, no polling needed
this.emit({ event: 'boardUpdated', data: result.board });
this.emit({ event: 'turnChanged', data: { next: result.nextPlayer } });
return result;
}
}
// In your custom UI (ui/chess.html)
// The global `chess` is auto-injected, named after your photon file
chess.onBoardUpdated(board => renderBoard(board));
chess.onTurnChanged(({ next }) => showTurn(next));
// Call server methods directly
chess.move({ from: 'e2', to: 'e4' });
A human moves through Beam. Claude is configured with the MCP server. The lock ensures they truly alternate. Events keep the board live on both sides. That's a fully functional turn-based chess game, human vs AI, in about 50 lines of application logic.
The same pattern applies beyond games: approval workflows where a human reviews before AI continues, collaborative tools where edits from any source appear instantly, simulations where steps must execute in strict sequence, any system where who acts next matters.
MCP Primitives on this
The MCP protocol's user-facing primitives are surfaced as plain methods on every photon instance — no decorators, no capability flags, no SDK imports. The runtime routes each call through whichever surface the request arrived on (Beam, Claude Desktop, Cursor, CLI).
export default class Editor {
async summarize(params: { text: string }) {
// Ask the driving agent's LLM. No API key. Agent pays.
return await this.sample({
prompt: `Summarize in one sentence:\n\n${params.text}`,
maxTokens: 128,
});
}
async deploy() {
if (!(await this.confirm('Ship to production?'))) return;
const env = await this.elicit<string>({
ask: 'select',
message: 'Which environment?',
options: ['staging', 'prod'],
});
await this.run(env);
}
}
| Primitive | What it does |
|---|---|
await this.sample({ prompt }) |
Delegates LLM generation to the caller's model via MCP sampling |
await this.confirm(question) |
Yes/no prompt — returns boolean |
await this.elicit(params) |
Arbitrary input (text, select, form, file, etc.) |
this.status(msg) / this.progress(v) |
Live feedback during long work; routes to SSE stream in Beam |
this.roots |
MCP workspace roots declared by the connected client (roots/list) |
this.notifyResourceUpdated(uri) |
Push notifications/resources/updated to subscribed clients |
Full reference: docs/reference/MCP-PRIMITIVES.md.
Remote Access: Claim Codes
By default every installed photon is visible to every connected MCP client. When you want to pair a remote agent with a subset of your photons — your phone driving Beam, a teammate reviewing one project, a CI agent scoped to a single directory — generate a claim code:
$ photon claim --scope /workspace/proj --ttl 4h --label "phone"
✓ Claim code: R3K-9QZ
Scope: /workspace/proj
Expires in: 4h
The remote client presents the code as the Mcp-Claim-Code header on
its MCP session. tools/list then only exposes photons whose source
lives under that directory. Sessions without a code keep full access —
the feature is strictly opt-in.
Full reference: docs/reference/CLAIM-CODES.md.
Marketplace
A curated set of photons is ready to install. The public gallery is now kept small on purpose: polished apps and tools in one place, teaching examples in another.
photon search boards
photon add boards
You can also install directly from any GitHub repository using qualified refs:
photon add owner/repo/photon-name
Browse the Photon Apps marketplace for ready-to-use photons, or the Photon Examples marketplace for focused learning examples. You can also host a private marketplace for your team: internal tools that stay off the public internet.
Commands
# Run
photon # Open Beam UI
photon mcp <name> # Run as MCP server
photon mcp <name> --dev # MCP server with hot reload
photon cli <name> [method] # Run as CLI tool
# Install from GitHub
photon beam owner/repo/name # Install & open in Beam
photon cli owner/repo/name method # Install & run via CLI
# Create
photon maker new <name> # Scaffold a new photon
# Build
photon build <name> # Compile to standalone binary
photon build <name> --with-app # Include Beam UI in binary
Photon MCP questions
How do I add Photon MCP to Claude Code?
Run claude mcp add photon -- npx -y @portel/photon in your terminal. Add --scope user to make it available in every project.
How do I add Photon MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do I install a Photon tool as an MCP server in Claude Desktop?
Run photon mcp install <name> to register it in Claude Desktop's config, then restart Claude Desktop. Alternatively use photon info <name> --mcp to print a JSON config snippet to paste into an AI client.
What surfaces can Photon generate from one TypeScript file?
Photon derives an MCP server, an embedded app UI, a CLI tool, a Beam web interface, plus web routes, schedules, webhooks, state, and audit history.
Does Photon require decorators or server boilerplate?
No. A plain exported TypeScript class with methods is a complete photon; Photon generates CLI, web UI, and MCP server from it.
What runtime does Photon require?
Photon requires Node.js 20 or later and compiles TypeScript internally, so no tsconfig.json is needed.
How does Photon validate parameters across interfaces?
A single param tag like @pattern is enforced in the Beam form, the CLI, and the MCP schema at once.