# How to connect Google Cloud Vision to OpenClaw (paste one key, 29 tools) > Connect Google Cloud Vision to OpenClaw with ClawLink: paste your Google Cloud Vision key once and 29 tools work from chat. No MCP server to run, nothing stored on your machine. Web version: https://claw-link.dev/openclaw/google-cloud-vision The usual route to Google Cloud Vision access for OpenClaw is an MCP server you configure and keep running, plus your own OAuth app or API keys. ClawLink gives OpenClaw a more practical Google Cloud Vision setup: install one ClawHub skill, connect Google Cloud Vision in the browser, and OpenClaw can call real Google Cloud Vision actions from any chat surface with no auth, token refresh, or tool wiring to build yourself. ## Setup It takes three steps to connect OpenClaw to Google Cloud Vision. 1. **Install ClawLink** — add the plugin to OpenClaw once. 2. **Connect Google Cloud Vision** — one-click OAuth in the ClawLink dashboard. 3. **Use it from chat** — ask OpenClaw in plain English. **Paste this into OpenClaw to set up ClawLink:** > I want to connect my apps to OpenClaw through ClawLink. > Please install the ClawLink plugin from ClawHub and enable it: `openclaw plugins install clawhub:clawlink-plugin` > When it is installed, tell me and stop. After I reply, give me the ClawLink pairing link. Setup notes, if you need them: https://claw-link.dev/skill.md **Alternative for any agent (no plugin needed):** if the OpenClaw plugin route isn't available or doesn't work, any AI agent with shell access can use the ClawLink CLI instead: ```bash npx -y @useclawlink/cli login # sign in via browser — no API key to paste npx -y @useclawlink/cli connect google-cloud-vision # connect Google Cloud Vision (browser OAuth) npx -y @useclawlink/cli actions google-cloud-vision # list available actions npx -y @useclawlink/cli run google-cloud-vision --input '' # execute (add --confirm for writes) ``` ### Install by command The setup prompt above does all of this in one paste. By hand, it is one install command plus a browser approval: ```bash openclaw plugins install clawhub:clawlink-plugin ``` Then ask OpenClaw to set up ClawLink. It starts browser pairing and prints an approval link — open it, approve the device, return to the chat, and say `done`. Finally, connect Google Cloud Vision in the [ClawLink dashboard](https://claw-link.dev/dashboard) — paste your Google Cloud Vision API key once. Verify the connection by asking OpenClaw: > Use Google Cloud Vision to annotate files and walk me through the result in plain English. ### Using a different agent? The OpenClaw plugin is one client of ClawLink's MCP server. Claude Code, Cursor, Codex, or any agent that can run a shell command pairs with the same ClawLink account through the CLI: ```bash npx -y @useclawlink/cli login ``` `login` opens the same browser approval and stores a credential locally. Once Google Cloud Vision is connected in the dashboard, that agent calls the same 29 Google Cloud Vision tools over MCP. Full setup for MCP clients and shell agents: [connect apps to any AI agent](https://claw-link.dev/learn/connect-apps-to-any-ai-agent). ## Google Cloud Vision MCP for OpenClaw Looking for a Google Cloud Vision MCP server for OpenClaw? ClawLink connects Google Cloud Vision to OpenClaw and exposes 29 Google Cloud Vision tools your agent can call over [MCP](https://claw-link.dev/learn/what-is-an-mcp-server), with [hosted auth](https://claw-link.dev/learn/oauth-for-ai-agents) and nothing to run or maintain yourself. Using Hermes instead? The [Hermes Google Cloud Vision integration](https://claw-link.dev/hermes/google-cloud-vision) works the same way. ## What the OpenClaw Google Cloud Vision integration can do 29 Google Cloud Vision tools are ready for OpenClaw once the account is connected. The 24 below are the ones people reach for most; your agent can call all 29. ### 24 of 29 Google Cloud Vision tools for OpenClaw | Tool | What it does | |---|---| | **Annotate files** `google_cloud_vision_annotate_files` | Perform image detection and annotation for batch files in Google Cloud Vision | | **Annotate images** `google_cloud_vision_annotate_images` | Run image detection and annotation for a batch of images using Google Cloud Vision API | | **Annotate location images** `google_cloud_vision_annotate_location_images` | Run image detection and annotation for a batch of images scoped to a specific project and | | **Get product** `google_cloud_vision_get_product` | Get information associated with a Product | | **Get product set** `google_cloud_vision_get_product_set` | Get a ProductSet | | **List index endpoints** `google_cloud_vision_list_index_endpoints` | Lists IndexEndpoints in Vertex AI Vision for a given project and location | | **List locations** `google_cloud_vision_list_locations` | List available Vision AI service locations for a project | | **List operations** `google_cloud_vision_list_operations` | List operations that match the specified filter | | **Vision get operation** `google_cloud_vision_vision_get_operation` | Retrieves the latest state of a long-running Vision API operation | | **Vision get reference image** `google_cloud_vision_vision_get_reference_image` | Get information associated with a ReferenceImage | | **Vision list products in product set** `google_cloud_vision_vision_list_products_in_product_set` | List Products in a specified ProductSet | | **Vision list projects** `google_cloud_vision_vision_list_projects` | List Google Cloud projects accessible to the authenticated user via Cloud Resource Manager API | | **Vision list reference images** `google_cloud_vision_vision_list_reference_images` | List reference images for a product | | **Annotate files async batch** `google_cloud_vision_annotate_files_async_batch` | Run asynchronous image detection and annotation for a list of generic files (PDF, TIFF, GIF) | | **Annotate images async batch** `google_cloud_vision_annotate_images_async_batch` | Run asynchronous image detection and annotation for a batch of images | | **Create product** `google_cloud_vision_create_product` | Creates a new Product resource in Google Cloud Vision Product Search | | **Create product set** `google_cloud_vision_create_product_set` | Creates a new ProductSet resource in Google Cloud Vision Product Search | | **Create reference image** `google_cloud_vision_create_reference_image` | Create a ReferenceImage under a product | | **Import product sets** `google_cloud_vision_import_product_sets` | Asynchronously imports product sets and reference images from a CSV file stored in Google Cloud | | **Update product** `google_cloud_vision_update_product` | Update a Product's mutable fields: displayName, description, and productLabels | | **Update product set** `google_cloud_vision_update_product_set` | Update a ProductSet resource | | **Vision add product to product set** `google_cloud_vision_vision_add_product_to_product_set` | Add a Product to a ProductSet in Google Cloud Vision Product Search | | **Vision remove product from product set** `google_cloud_vision_vision_remove_product_from_product_set` | Removes a Product from a specified ProductSet in Google Cloud Vision API | | **Vision cancel operation** `google_cloud_vision_vision_cancel_operation` | Starts asynchronous cancellation of a long-running Vision API operation | ## Example prompts **Annotate Files** > Use Google Cloud Vision to annotate files and walk me through the result in plain English. **Annotate Images** > Use Google Cloud Vision to annotate images and walk me through the result in plain English. **Annotate Location Images** > Use Google Cloud Vision to annotate location images and walk me through the result in plain English. **Get Product** > Pull the relevant data from Google Cloud Vision, summarize it in plain English, and point out anything that needs attention. ## ClawLink vs. building it yourself The alternative to ClawLink is usually manual API key setup plus your own token handling, permission troubleshooting, and tool plumbing for OpenClaw. That is fine if you want to build and maintain the integration yourself. Most teams just want Google Cloud Vision working from chat. | | Manual | ClawLink | |---|---|---| | **Credential handling** | Collect, validate, store, and rotate the Google Cloud Vision API key yourself, then make sure every tool call uses the right account. | Users complete the hosted ClawLink setup once and the connected Google Cloud Vision account becomes available to the agent without you building credential management. | | **Ongoing maintenance** | You own refresh logic, permission debugging, environment config, and every provider-specific edge case for Google Cloud Vision. | ClawLink handles the repetitive integration plumbing so your team can focus on the workflow instead of the infrastructure. | | **Agent usability** | You still need to expose the right Google Cloud Vision actions to the runtime in a format your agent can reliably use. | 29 tools for Google Cloud Vision are already exposed through ClawLink, so the agent can read and act from chat immediately. | ## ClawLink vs. Composio Composio also exposes Google Cloud Vision to AI agents. It is developer infrastructure: Python and TypeScript SDKs, an MCP server, and a catalog past 1,000 apps, aimed at teams shipping agent products. ClawLink is built for OpenClaw users instead. You install the plugin once, connect Google Cloud Vision in the browser, and the 29 tools above work from chat. There is no SDK and no config file, and the Google Cloud Vision key you paste at setup is stored server-side rather than kept in your environment. Choosing between them? Read the full [Composio alternatives](https://claw-link.dev/hub/composio-alternatives) comparison. ### OpenClaw installed the Google Cloud Vision skill but can't call the tools The ClawHub skill teaches OpenClaw about Google Cloud Vision, but the calls run through the ClawLink plugin and your connected account. Make sure Google Cloud Vision is connected in the dashboard, then start a fresh chat so OpenClaw reloads the tool catalog. If OpenClaw runs as a persistent gateway, restart it so the new tools register. ### Connection succeeds but no tools appear Reconnect Google Cloud Vision from the dashboard, then start a fresh chat if the runtime still has the old tool catalog loaded. ### "Tool schema not loaded yet" error when calling Google Cloud Vision tools Google Cloud Vision tool schemas load on demand the first time a tool runs and are cached after that, so this error usually clears on its own: wait a few seconds and retry the same request. If every Google Cloud Vision call keeps failing with it in a fresh chat, reconnect from the dashboard, and contact support if it still persists — that pattern points to a configuration problem on our side, not something you can fix by reconnecting again. ### Google Cloud Vision returns 403 or "permission denied" on one action while others work Two usual causes. The connected account may not have access to the specific workspace, inbox, store, or project in the request — check that first. If access looks right, the agent may have sent a placeholder value (like "YOUR_ID" or an example id from documentation) instead of a real one: ask it to run a list or search tool first, then retry the action with a real id from those results. Most failures at this stage are one of these two, not ClawLink bugs. ### API key setup works but results look incomplete Double-check that the API key for Google Cloud Vision has the right scopes or account access. A valid key can still be too limited for some reads or writes. ### Is there a OpenClaw Google Cloud Vision integration? Yes. ClawLink is the fastest way to connect OpenClaw to Google Cloud Vision: link your Google Cloud Vision account once in the browser and OpenClaw can call the Google Cloud Vision API through 29 ready-made tools — no custom code or token handling. ### How do I add Google Cloud Vision to OpenClaw with ClawLink? Paste the setup prompt from this page into OpenClaw. It installs the ClawLink Google Cloud Vision skill from ClawHub, then you click Connect in the dashboard to authorize Google Cloud Vision. OpenClaw calls the tools from the next message — no config files, and the Google Cloud Vision key you paste is stored server-side instead of in your environment. ### How long does it take to connect Google Cloud Vision to OpenClaw? About two minutes. Sign in, click Connect next to Google Cloud Vision in the dashboard, authenticate, and OpenClaw can use it from the next chat message. ### Why use ClawLink instead of wiring Google Cloud Vision up myself? The alternative to ClawLink is usually manual API key setup plus your own token handling, permission troubleshooting, and tool plumbing for OpenClaw. That is fine if you want to build and maintain the integration yourself. Most teams just want Google Cloud Vision working from chat. ### OpenClaw installed the Google Cloud Vision skill but can't call the tools The ClawHub skill teaches OpenClaw about Google Cloud Vision, but the calls run through the ClawLink plugin and your connected account. Make sure Google Cloud Vision is connected in the dashboard, then start a fresh chat so OpenClaw reloads the tool catalog. If OpenClaw runs as a persistent gateway, restart it so the new tools register. ## Related - [OpenClaw DataRobot integration](https://claw-link.dev/openclaw/datarobot) — DataRobot is a machine learning platform that automates model building, deployment, and monitoring, enabling organizations to derive predictive insights from large datasets. - [Chatbotkit tools](https://claw-link.dev/openclaw/chatbotkit) — ChatBotKit is a platform that enables developers to build and manage AI-powered chatbots, offering comprehensive APIs and SDKs for seamless integration into applications. - [OpenClaw Just One API integration](https://claw-link.dev/openclaw/just-one-api) — Just One API provides unified access to public social media, creator, entertainment, and ecommerce data across hundreds of metered endpoints.