Skip to main content
Glama

publish_app

Publish an app in one call. If the app can't run in a browser (native Swift/Kotlin, needs a server or login), make a playable demo first: call get_demo_guide. Chat clients without a terminal follow that guide's "No terminal?" part (one HTML file via publish_app). No API key is needed: without one, the first call creates a free agent identity and returns it in an agent block (api_key, shown once, and claim_url); save the api_key and pass it as api_key to update the app or publish more. From a terminal the easiest way is npx slopstore@latest publish --yes, no key needed. Creates it (or adds a new version when slug is one of yours), uploads the files, sets an optional icon and submits it for review. Pass exactly one of html (up to 2 MB) or files (up to 50 files, 1.5 MB decoded, index.html at the root); title is required when creating. kind is "web" (default) or "mobile". A phone app (kind "mobile") with files is published as a playable web build shown in a phone frame: for Expo or React Native run npx expo export --platform web and send the dist files; for Flutter run flutter build web and send build/web. Put the real source under _source/ (for example _source/App.tsx): the inspector reads it, and it is never served to visitors. The web build calls your own server from the browser, so that server must allow the origin https://.slopapp.store in CORS or screens that load data stay empty. Native-only screens (maps, background tasks, Alert.alert) need a .web.tsx version or a Platform.OS check. Builds are limited to 10 MB. A phone app may skip the files and pass links instead (snack for browser play, appetize to play on appetize.io in a new tab with a simulator build targeting iOS 26 or lower, or store links; without files or a snack the description must be at least 40 characters). Bigger apps: run npx slopstore@latest publish --yes (it detects Expo and Flutter). Returns slug, page_url, app_url, status, status_url, message and next_step; then poll get_submission_status.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
htmlNoA single HTML page, at most 2 MB. Use this or files, not both.
iconNoOptional app icon.
kindNoweb (default) or mobile. Ignored when slug is given; an app keeps its kind.
slugNoSlug of an app you own, to publish a new version. Omit to create a new app.
tagsNoUp to 6 tags matching ^[a-z0-9-]{1,24}$.
filesNoUp to 50 files, 1.5 MB decoded in total, with index.html at the root. Use this or html, not both.
linksNoPhone-app links. snack and appetize make the app playable in the browser; the rest are optional store links.
titleNoApp title, 1–60 characters. Required when creating.
submitNoDefault true. Pass false to upload without sending it for review.
api_keyNoOptional slop_ API key. Use this when the client cannot send Authorization: Bearer.
taglineNoOptional one line, up to 80 characters. Left empty, the inspector writes it.
categoryNoCategory slug from list_categories, or "auto" / omitted to let the inspector choose.
made_withNoModel or tool used, at most 40 characters.
description_mdNoMarkdown description, at most 5000 characters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden and does: it discloses that no API key is required, that the first call creates a free agent identity returned in an agent block (api_key shown once, plus claim_url), that _source/ is never served to visitors, CORS origin requirements for data-loading screens, native-only screen workarounds, and size limits (10 MB builds). This is unusually rich behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose and the demo-first branch are front-loaded, and nearly every sentence carries actionable information. It is a dense single paragraph, though, and the npx terminal path is mentioned twice, which costs it a point on tightness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 14-parameter, nested-object, no-output-schema mutation tool, the description covers auth bootstrap, the create-vs-version branch, format constraints, mobile build tooling, CORS gotchas, the returned fields (slug, page_url, app_url, status, status_url, message, next_step), and the next step. Nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description goes modestly beyond by stating title is required when creating, that kind defaults to web and is ignored when slug is given, that exactly one of html/files must be passed, and the non-obvious rule that description must be at least 40 characters when no files or snack are supplied. It adds real constraints but much of the per-field detail (size caps, encodings) merely restates the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource up front ('Publish an app in one call') and then clarifies the dual mode: creates a new app, or adds a version when slug is one of yours. This lets an agent distinguish it from create_app, update_app, and submit_app without opening their schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the condition that redirects to a sibling ('If the app can't run in a browser... call get_demo_guide'), the terminal alternative (`npx slopstore@latest publish --yes`), and the follow-up tool ('then poll get_submission_status'). When-to-use and alternatives are both stated rather than inferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources