Design

theagentc.io

An MCP server for managing App Store apps and using Claude to art-direct and generate full App Store screenshot sets.

1 endpoint10 known toolsFirst detected October 5, 2026Last detected October 5, 2026

ENDPOINT 1

https://api.theagentc.io/mcp

No auth detected

MCP server metadata

Name: agent-c
Version: 1.0.0

Capabilities

tools

Server instructions

Agent C designs App Store screenshot sets from an app's real screenshots. Typical flow: 1. list_apps (or add_app with the App Store link). 2. Upload 4-10 raw screenshots of the app: get_upload_link + curl if you have a shell (preferred), else upload_screenshots (base64 or public https URLs). 3. design_set — Claude art-directs the whole set (opening shot, headlines, close-ups, colors). Returns watermarked previews + a studio link. ~40-60s. 4. edit_set to change headlines, screenshots, order, layout or the opening shot (instant, free). 5. To get clean files: unlock_set (uses a free unlock if available, else returns a $9.99 checkout link the USER must open; Studio subscribers are already unlocked), then export_set (PNG download links) or send_to_app_store (uploads into the app's draft version in App Store Connect; never submits for review). Always show the user the previews and ask before paying, creating an App Store version, or replacing screenshots in App Store Connect. Headlines use *stars* around the words to color.

Known tools 10

list_apps

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

Inferred read-only

add_app

Add an app by its App Store link (imports name, icon, description), or by name if it isn't released yet.

Inferred read-only

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).

Potential side effects

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).

Potential side effects

design_set

Claude art-directs a full App Store screenshot set from the uploaded screenshots: opening shot, headline per slide, close-ups, palette.

Inferred read-only

get_set

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

Inferred read-only

edit_set

Change one slide (headline, subline, screenshot, layout, position, or remove it), the opening shot, or the device size.

Potential side effects

unlock_set

Unlock clean, full-resolution files for a set.

Inferred read-only

export_set

Render the unlocked set at exact App Store pixels without watermark and return download links (valid 7 days).

Inferred read-only

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.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agent-c]
url = "https://api.theagentc.io/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agent-c": {
      "type": "http",
      "url": "https://api.theagentc.io/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agent-c
Remote MCP URL: https://api.theagentc.io/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agent-c": {
      "url": "https://api.theagentc.io/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agent-c": {
      "type": "http",
      "url": "https://api.theagentc.io/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agent-c",
  "transport": "streamable-http",
  "url": "https://api.theagentc.io/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.