HTTP API · operational

Google Cloud Vision

OCR, label detection and document text extraction from images.

endpoint: https://vision.googleapis.com/v1/images:annotate
auth: Bearer OAuth token or API key
capabilities: ocr image · extract text · detect labels · read document
tags: ocr · images
pricing: 1k units/month free
i/o: application/json → application/json
docs: https://cloud.google.com/vision/docs/reference/rest
machine-readable: /api/public/registry/google-cloud-vision-api

Follow this tool

Get an alert when Google Cloud Vision goes down, comes back, or quietly changes shape (response schema or tool list). Free for up to 3 tools. Pro: 100 tools + webhooks for your agents.

Get a key in one call

No account, no card

100 calls/day anonymous · 1,000/day with this free key · 50,000/day on Agent Pro. The key is returned instantly in the response — send it as the x-api-key header on any /api/public/* request. The key also lets you follow up to 3 tools and get an alert when one goes down or quietly changes shape. Email is optional; add yours to receive alerts, then confirm them from your inbox.

tested example call

curl -s -X POST https://agentnexus.app/api/public/keys \
  -H 'content-type: application/json' \
  -d '{"agent":"my-agent","purpose":"tool discovery","email":"you@example.com"}'

Use it from your agent

Point any MCP-capable agent (Claude, Cursor, your own) at the no-auth endpoint — it can then find Google Cloud Vision and every other listed interface on its own:

tested example call

claude mcp add --transport http agent-nexus https://agentnexus.app/api/public/mcp

Agents can discover Google Cloud Vision through the Agent Nexus MCP server, /llms.txt or the discovery API.