Google Cloud Vision for AI agents
Google Cloud Vision API enables developers to integrate vision detection features into applications, including image labeling, face and landmark detection… Add an API key once and every agent you run can use it.
- Connects with an API key
- Ready to connect
- Any MCP client
- No card required
The route from an agent to Google Cloud Vision
Once Google Cloud Vision is set up in your workspace, any agent you run can reach it: a Spinrun agent, or Claude, ChatGPT and Cursor through one MCP endpoint. Every call passes through the Spinrun gateway, which sorts it by risk and writes it to the activity log.
By default, every change an agent makes in a connected app waits for your approval, on every plan. Enhanced Control, on Pro and up, adds per-app read, write and destructive rules at the gateway.
Google Cloud Vision in the catalog
Google Cloud Vision API enables developers to integrate vision detection features into applications, including image labeling, face and landmark detection… · AI & Machine Learning
- An agent gets a jobFrom chat, a schedule, or your own AI client
- Spinrun checks the callSorted as a read, a write or a destructive call
- Google Cloud Vision does the workThrough the connection you set up in your workspace
- Every call is loggedTool, outcome and duration, in one activity log
Three steps
From connection to first call
Connect an app once
Sign in from your workspace with OAuth or an API key. Spinrun keeps the credential in an encrypted vault, never in an agent's config.
Decide what it may do
By default, every change an agent makes in a connected app waits for your approval, on every plan. On Pro and up, Enhanced Control adds per-app rules for reads, writes and destructive calls.
Let any agent use it
Claude, ChatGPT, Cursor or a Spinrun agent reach the app through one MCP endpoint, and every call is written to the same activity log.
What it can do
Every Google Cloud Vision action, sorted by risk
Spinrun sorts every Google Cloud Vision action into one of three tiers. By default, agents ask before a write, on every plan; on Pro and up, the rules you set decide which tiers run.
- Reads
Read actions
Fetch and search. Cannot change anything.
- Writes
Write actions
Create and update. Changes data but does not remove it.
- Destructive
Destructive actions
Delete, revoke, or overwrite. Hard or impossible to undo.
Same category
Other AI & Machine Learning apps
Other apps in this category that your agents can use.
Questions about Google Cloud Vision
You paste an Google Cloud Vision API key once. Spinrun keeps it in an encrypted vault rather than in an agent's config, and you can revoke it in one click.
Put Google Cloud Vision to work. Start free.
Connect Google Cloud Vision, decide what it may do, and give an agent its first job.