INDIVIDUAL MCP TOOL

list_collections

The workspace's hand-curated photo collections (name, id, count).

tagrly.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://tagrly.com/mcp

No auth detected

Connect to this endpoint to inspect the live schema for list_collections and invoke it with your own arguments.

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

CONNECT WITH APPROVAL

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

Codex

~/.codex/config.toml

[mcp_servers.tagrly]
url = "https://tagrly.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "tagrly": {
      "type": "http",
      "url": "https://tagrly.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: tagrly
Remote MCP URL: https://tagrly.com/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": {
    "tagrly": {
      "url": "https://tagrly.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "tagrly": {
      "type": "http",
      "url": "https://tagrly.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "tagrly",
  "transport": "streamable-http",
  "url": "https://tagrly.com/mcp"
}

MCP Inspector

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

search_photos — Instant keyword search over the workspace's analyzed photos.
find_photos — Plain-language photo search: a model interprets the sentence, resolves it into filters, and reranks a candidate pool.
get_page_images — The one-call page builder: send a plain-English page topic, get back a curated set of images organized into slots (hero, grid, detail) with rewritten alt text per pick and an honest gap_signal naming shots the library does not have.
get_image — Full stored analysis for a single photo by drive_id: long description, all tags, folder path, everything.
log_usage — Record that photos were rendered (which page, which slot) so future get_page_images calls with exclude_recently_used_days can avoid repeats.
import_images — Fetch images from URLs into this workspace's library, where they are AI-tagged and become searchable within minutes.