Skip to content
Agent C logo

Agent C MCP server

Which servers in the official MCP registry are Agent C's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-20

← Back to Agent C

Whose server it is
  • Registry nameio.theagentc/app-store-screenshotsverified in the MCP registry

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

When we asked itchecked 2026-10-20
  • Stateanswerschecked 2026-10-20
  • Tools10
  • Server calls itselfagent-c
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 198 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: Turn raw simulator screenshots into a designed App Store set; Write headlines from real app numbers for each screen.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "Turn raw simulator screenshots into a designed App Store set", the likely first call is list_apps.
  • add_app, upload_screenshots, design_set, edit_set, unlock_set change data without a sign-in: anyone with the address can call them.
  • Parameters are untyped or undescribed in 4 of 10 tools: check arguments before calling.

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 2026-10-20
  • 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 answer173 ms
  • Space in an agent's context≈ 1,572 tokensthe definitions of all its tools (10), which an agent carries on every turn
  • Tool definitionsA · 93 of 100
  • Typed results0 of 10 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 4 of 10

What an agent can do with it

  • can do · Turn raw simulator screenshots into a designed App Store set
  • can do · Write headlines from real app numbers for each screen

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: add_app, upload_screenshots, design_set, edit_set, unlock_set

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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 offers10 tools · read 2026-10-20
  • list_apps

    The user's apps in Agent C, with how many screenshots each has uploaded.

  • add_app

    Add an app by its App Store link (imports name, icon, description), or by name if it isn't released yet. Importing a live app takes ~10-30s; poll list_apps until status is 'ready'.

  • get_upload_link

    Best way to upload screenshots from files on disk: returns a one-time URL (valid 30 min) to POST the image files to with curl (multipart field 'files', up to 10 per request). Use this instead of upload_screenshots when you have a shell…

  • upload_screenshots

    Upload 1-10 raw screenshots of the app (plain captures of the real UI, ideally 4-10, in the order you'd like them considered). Each item is base64 image data (PNG/JPEG) or a public https URL. By default replaces the app's screenshot…

  • design_set

    Claude art-directs a full App Store screenshot set from the uploaded screenshots: opening shot, headline per slide, close-ups, palette. Returns watermarked preview images, the slide list and a link to open it in the Agent C studio. Takes…

  • get_set

    Current slides, unlock status and fresh preview images for a set.

  • edit_set

    Change one slide (headline, subline, screenshot, layout, position, or remove it), the opening shot, the device size, or the App Store header (header_*). Re-renders previews. Free.

  • unlock_set

    Unlock clean, full-resolution files for a set. Uses a free unlock if the user has one; otherwise returns a $9.99 Stripe checkout link the USER must open and pay. Studio subscribers are already unlocked. Ask the user before calling.

  • export_set

    Render the unlocked set at exact App Store pixels without watermark and return download links (valid 7 days). Includes the product page header (3840x1646) and search-results image (3840x2560) when the set has a header.

  • send_to_app_store

    Upload the unlocked set into the app's editable version in App Store Connect, replacing that language's screenshots for this device size. Never submits for review. Requires the user to have connected App Store Connect in Agent C. If the…

How to connect

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

{
  "mcpServers": {
    "app-store-screenshots": {
      "type": "http",
      "url": "https://api.theagentc.io/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http theagentc https://api.theagentc.io/mcp

Add to CursorAdd to VS Code

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

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.