microfn

microfn is a sandboxed cloud environment for building, deploying, and running tiny JavaScript functions - designed to be AI-friendly. Give ChatGPT its own workspace to write functions, deploy them, manage their code and secrets, and run the functions you've already built. With microfn, ChatGPT can: - Write and deploy a new JavaScript function on request - Inspect, update, and validate the code of existing functions - Manage function settings and secrets securely - Run your functions and use their results in the conversation Each function runs in an isolated sandbox, so ChatGPT can safely create and compose its own tools - fetch a weather API, build a key-value store, post to Slack, send a Telegram message, and much more.

View in the ChatGPT registry

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Developer Tools
Primary Subcategory: App Hosting & Deployment Platforms
Secondary Subcategories: None listed
Brand: microfn
Access: Account required
First tracked: 2026-08-14
Tool count: 17
Geography: US

ChatGPT Plugin Discoverability Score

ChatGPT organic discovery is not live yet

microfn is tracked in the ChatGPT Plugin registry. Public organic-discovery measurement is not live for ChatGPT yet, so there is no score to publish today.

Get notified when your score goes live

Enter your work email and we’ll notify you when ChatGPT Plugin organic discovery scoring launches.

No spam. Unsubscribe any time.

Talk to our team

Primary Subcategory

Competing in ChatGPT App Hosting & Deployment Platforms

View Category

Listed in alphabetical order

Primary Subcategory

AlpicOrganic discovery is pendingGet the score at launch

AlpixOrganic discovery is pendingGet the score at launch

Catalyst by ZohoOrganic discovery is pendingGet the score at launch

iAhorro HipotecasOrganic discovery is pendingGet the score at launch

ManufactOrganic discovery is pendingGet the score at launch

microfnOrganic discovery is pendingGet the score at launch

Score explained

How the Discoverability Score works

Organic discovery scoring for microfn on ChatGPT is not live yet. The score will use measured agent conversations when it launches.

InvisibleBuriedEmergingCompetitiveWinning

Organic discovery scoring is pending. Your Plugin score will appear on this scale when measurement goes live.

FoundDiagnostic

Whether Claude found your Plugin in connector search. It must be Found before it can reach the picker, but the score counts picker appearances—not search results.

PickedMain score

How often your Plugin appeared in the picker, or Claude invoked it directly, across contested conversations. This percentage is the Discoverability Score; the headline number is rounded.

PositionedDiagnostic

What position your Plugin appeared in when it was shown in the picker. This shows prominence, but it does not affect the score.

Read the full scoring methodology Recommended guideHow to get your Claude Connector organically discoveredFollow the practical steps agents use to find, shortlist, and choose your Connector.

Tools

17 tools agents can invoke

Validate and lint TypeScript code snippet for MicroFn. Returns validation results and package extraction summary.
Check the deployment status of a function. Requires functionName parameter in format 'username/functionName'.
Create a new MicroFn workspace/function with TypeScript code. The code must export either: 1) A 'main' function as the entry point, OR 2) Any named function (which will be auto-wrapped with a main function). Examples: 'export async function main() { return "hello" }', 'export async function sayHello(name) { return "hello " + name }' (auto-wrapped), 'export async function main() { const btc = await fetch("..."); return btc.json() }'. IMPORTANT: Import @microfn/* modules as defaults: 'import kv from "@microfn/kv"' NOT 'import { kv } from "@microfn/kv"'. Common patterns: use @microfn/secret for env vars, @microfn/kv for persistent storage (e.g., counters, cache), and fetch() for HTTP requests. Input: 'name' (string) - the function name, 'code' (string) - the TypeScript code. Output: the created workspace object with its name and metadata.
Creates a new secret for the specified function. Secrets cannot be overwritten; if the key already exists, delete it first.
Deletes a secret from the specified function
Execute a function with given input. Requires functionName (format: 'username/functionName') and optional inputData parameters.
Generate a new function from a natural language prompt. Returns one or more code variations.
Get details of a function (no source code). Use getFunctionCode for code. Requires functionName parameter in format 'username/functionName'.
Get the source code of a function. Requires functionName parameter in format 'username/functionName'.
Retrieves all secrets for the specified function
List all available MicroFn workspaces/functions. Returns an array of workspaces with username and name that can be used with other tools.
Lists packages from the latest deployment. Requires functionName parameter in format 'username/functionName'.
Simple ping tool to test connectivity
Rename a function/workspace
Update the source code of a function. The code can export either: 1) A 'main' function directly, OR 2) Any named function (auto-wrapped). Examples: Bitcoin price fetcher: 'export async function main() { const res = await fetch("https://api.coingecko.com/api/v3/simple/price?ids=bitcoin&vs_currencies=usd"); return { price_usd: (await res.json()).bitcoin.usd }; }'. With KV counter: 'import kv from "@microfn/kv"; export async function main() { const count = (await kv.get("visits")) || 0; await kv.set("visits", count + 1); return { visits: count + 1 }; }'. IMPORTANT: Always use default imports for @microfn/* modules. Requires functionName (format: 'username/functionName') and code parameters.
Update settings for a function, such as enabling/disabling MCP tool exposure.
Wait for a function deployment to complete. Uses PubSub integration for real-time updates with 30-second timeout. Returns immediately if not currently deploying.

microfn FAQ

How do I improve a ChatGPT Plugin's discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

What are microfn alternatives on ChatGPT?

As of 2026-08-14, microfn competes with Alpic, Alpix, Catalyst by Zoho, iAhorro Hipotecas, Manufact, Netlify, Railway, Render, Send Postcard, ShipStatic, Vercel in ChatGPT App Hosting & Deployment Platforms, ranked by public Discoverability Score.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.