CraterView MCP

The CraterView MCP server allows AI assistants to perform image enhancement, restoration, and upscaling tasks using CraterView's proprietary models. It provides tools to enhance images by reconstructing details and restoring damaged photos by removing scratches and correcting colors. The server handles authentication via a secure code exchange and manages job status, enabling agents to upscale, sharpen, or repair images directly within their workflows.

Endpoint and access

OAuth sign-in: the first time you connect, your client opens the vendor's own authorization prompt in a browser.

OAuth sign-inEndpoint checked 2026-10-18Operated by CraterView

MCP endpoint (Streamable HTTP)

https://mcp.craterview.ai/mcp

Vendor documentation

What you can do with it

Upscale low-resolution images to higher dimensions
Restore damaged, torn, or faded historical photographs
Sharpen soft or blurry photos to improve clarity
Generate professional headshots from casual photos

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http craterview-mcp https://mcp.craterview.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add craterview-mcp --url https://mcp.craterview.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable craterview-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "craterview-mcp": {
      "url": "https://mcp.craterview.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

{
  "mcpServers": {
    "craterview-mcp": {
      "type": "streamableHttp",
      "url": "https://mcp.craterview.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start craterview-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "craterview-mcp": {
      "type": "http",
      "url": "https://mcp.craterview.ai/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http craterview-mcp https://mcp.craterview.ai/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "craterview-mcp": {
      "url": "https://mcp.craterview.ai/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "craterview-mcp": {
      "serverUrl": "https://mcp.craterview.ai/mcp"
    }
  }
}

See all 215

Do you run CraterView MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing