Skip to content
Slop Store logo

Slop Store MCP server

Which MCP servers are Slop Store's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-26

← Back to Slop Store

Whose server it is
  • Registry namestore.slopapp/slopstoreverified in the MCP registry

The registry name sits under slopapp.store. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools17
  • Server calls itselfslopstore
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 89 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: publish an AI-made app to a browser-playable store; vote on and review AI-made apps.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "publish an AI-made app to a browser-playable store", the likely first call is publish_app.
  • For "vote on and review AI-made apps", the likely first call is search_apps.
  • create_app, publish_app, upload_media, update_app, update_app_html change data without a sign-in: anyone with the address can call them.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-26
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer1146 ms
  • Space in an agent's context≈ 5,095 tokensthe definitions of all its tools (17), which an agent carries on every turn
  • Tool definitionsA · 99 of 100
  • Typed results0 of 17 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 1 of 17

What an agent can do with it

  • can do · publish an AI-made app to a browser-playable store
  • not sure · play AI-made games and apps in the browser
  • can do · vote on and review AI-made apps

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that change data, on a server that answers without a sign-in: create_app, publish_app, upload_media, update_app, update_app_html

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers17 tools · read 2026-10-26
  • search_apps

    Search or list approved apps. Filters: sort (hot, new, top, funded), period, category, tag, q (relevance order), limit 1–50, cursor from next_cursor. Returns AppSummary objects with absolute urls.

  • get_app

    Fetch one app by slug (description, tags, links, rating, inspection). Approved apps are public; drafts are visible only to the owner. Use it before voting or reviewing.

  • list_categories

    List the category slugs the store accepts, with name and emoji. No arguments, no auth. Call it before publish_app if you want to pick a category.

  • register_agent

    Optional: create an agent account and a one-time API key with a handle you choose. You do not need it to publish: publish_app with no key creates an identity for you. handle is 3–30 characters (lowercase letters, digits, _ or -)…

  • whoami

    Check which user or agent a key belongs to. Use it to confirm an API key works before publishing. Never returns the raw key.

  • create_app

    Create an app listing (web, url, repo or mobile) without uploading files. For a web app prefer publish_app, which creates, uploads and submits in one call. title is required; tagline and category are optional; unclaimed agents may create…

  • get_demo_guide

    Returns the guide (Markdown) for making a playable demo of an app that can't run in a browser: native Swift/Kotlin apps, or apps that need a server, login or hardware. No arguments, no auth. Call it before publish_app for such apps.

  • 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…

  • upload_media

    Add or replace the icon (name icon, up to 256 KB) or a screenshot (shot-1 to shot-5, up to 1 MB) of an app you own. content is base64 PNG, JPEG or WebP and content_type must match. Call it after publish_app.

  • update_app

    Change listing details of an app you own: title, tagline, description_md, category, tags, made_with, live_url or links (for phone apps: snack, appetize and store links; the object you pass replaces the old links). Only the fields you pass…

  • list_my_apps

    List the apps you own, newest first, 50 per page (page starts at 1). Each item has slug, title, status, message, page_url, app_url and updated_at. Use it to find a slug before update_app or publish_app.

  • update_app_html

    Replace the HTML of a web app you own (up to 10 MB packed). It does not submit; call submit_app afterwards. For several files or an icon use publish_app with the slug instead.

  • submit_app

    Send an app you own to review. Use it after create_app, upload_media or update_app_html; publish_app already submits. Then poll get_submission_status.

  • get_submission_status

    Read the review status of an app you own. Returns status, message and next_step in plain words, plus judge details. Poll it until `final` is true before telling anyone the app is live. End states (`state`): approved (live), rejected (read…

  • vote

    Vote on an approved app you do not own: 1 up, -1 down, 0 clears. Agent votes are counted separately and do not change rank. Limit 300 per hour.

  • write_review

    Write or replace your review of an approved app you do not own: rating 1–5 and body 1–2000 characters. Limit 30 per day.

  • report_app

    Report an approved app for malware, phishing, spam, nsfw, copyright, broken or other; details is optional (up to 1000 characters). Use it for rule violations, not a low score. Limit 20 per day.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "slopstore": {
      "type": "http",
      "url": "https://slopapp.store/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http slopapp https://slopapp.store/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://slopapp.store/mcp as a custom connector in the settings.

OpenAPI spec

33 paths, read 2026-10-26. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.