Headshot Photo Check

Check the technical quality of a professional profile or job-application photo from your assistant. This English-language MCP server returns measurable issues and practical tips for LinkedIn, XING and applications.

Connection details

Two read-only tools

check_headshot_photo

Checks resolution, crop/aspect ratio, size and format. When pixel analysis is available, it also checks brightness, contrast, overall color balance, border-background clutter and coarse sharpness. Returns a score from 0–100, prioritized tips, crop recommendations and coverage notes. The score covers only the criteria actually checked; some results are header-only. Face framing needs manual review.

Supply exactly one image_url (a public HTTPS image URL) or image_base64 (JPEG, PNG or WebP), up to 8,000,000 decoded bytes. The optional target is linkedin, xing, application or all (default). URL checks fetch the image from the public host you specify; that host receives a network request. Prefer a URL without secrets, as large base64 requests can exceed runtime limits.

get_headshot_photo_requirements

Returns a static checklist for dimensions, formats, preparation and recommended crops. Accepts the same optional target values and needs no photo. These are recommendations, rather than official platform limits.

Both tools are read-only: they do not modify your files or publish anything. Images and URLs are processed in memory and are not stored by the application. The service does not generate or return edited images, identify people or judge personal attributes. Assistant and infrastructure providers have their own data handling; see the privacy policy.

Add it to your assistant

Custom connector availability and menu names depend on your account, workspace permissions and client version.

Claude (claude.ai)

  1. Open Settings > Connectors > Add custom connector.
  2. Enter Headshot Photo Check as the name and https://mcp.profilfoto-ki.de/mcp as the server URL.
  3. Save the connector, enable it in your conversation and ask for a checklist or photo check. No server authentication is needed.

Claude Code

  1. Run this command in your terminal:
claude mcp add --transport http headshot-photo-check https://mcp.profilfoto-ki.de/mcp

Open Claude Code and use /mcp to check the connection, then ask for a photo checklist.

ChatGPT

  1. Open Settings > Apps & Connectors (called Apps in some versions). Enable developer mode under Advanced settings if your account permits it.
  2. Choose Create or Add connector. Enter Headshot Photo Check and the URL https://mcp.profilfoto-ki.de/mcp. Select no authentication if prompted.
  3. Save, start a chat and select the connector from the apps/tools menu. Ask for the LinkedIn photo checklist to verify the connection.

In newer interfaces, open ChatGPT Plugins, select the plus button, then Add custom MCP server and enter the same name and URL. See OpenAI’s connection guide for current account and setup details.

Codex CLI

  1. Run:
codex mcp add headshot-photo-check --url https://mcp.profilfoto-ki.de/mcp

Alternatively, add this entry to ~/.codex/config.toml:

[mcp_servers.headshot-photo-check]
url = "https://mcp.profilfoto-ki.de/mcp"

Start Codex and use /mcp to verify the server. See the official MCP configuration guide.

Cursor

  1. Add the following to your project’s .cursor/mcp.json, merging it with any existing mcpServers entries:
{
  "mcpServers": {
    "headshot-photo-check": {
      "url": "https://mcp.profilfoto-ki.de/mcp"
    }
  }
}

Open Cursor’s MCP settings, enable the server and confirm both tools appear. Ask for a checklist in the assistant.

Try it

Start without a photo: “What crop and resolution should I prepare for XING?” For a photo check, ask: “Check my LinkedIn headshot at this public HTTPS image URL and prioritize improvements,” followed by a URL you are authorized to share.

Read the privacy policy, terms of use and support and troubleshooting guide.