# How to connect Scale ai to OpenClaw (paste one key, 40 tools) > Connect Scale ai to OpenClaw with ClawLink: paste your Scale ai key once and 40 tools work from chat. No MCP server to run, nothing stored on your machine. Web version: https://claw-link.dev/openclaw/scale-ai The usual route to Scale ai 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 Scale ai setup: install one ClawHub skill, connect Scale ai in the browser, and OpenClaw can call real Scale ai 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 Scale ai. 1. **Install ClawLink** — add the plugin to OpenClaw once. 2. **Connect Scale ai** — 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 scale-ai # connect Scale ai (browser OAuth) npx -y @useclawlink/cli actions scale-ai # list available actions npx -y @useclawlink/cli run scale-ai --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 Scale ai in the [ClawLink dashboard](https://claw-link.dev/dashboard) — paste your Scale ai API key once. Verify the connection by asking OpenClaw: > Pull the relevant data from Scale ai, summarize it in plain English, and point out anything that needs attention. ### 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 Scale ai is connected in the dashboard, that agent calls the same 40 Scale ai 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). ## Scale ai MCP for OpenClaw Looking for a Scale ai MCP server for OpenClaw? ClawLink connects Scale ai to OpenClaw and exposes 40 Scale ai 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 Scale ai integration](https://claw-link.dev/hermes/scale-ai) works the same way. ## What the OpenClaw Scale ai integration can do 40 Scale ai tools are ready for OpenClaw once the account is connected. The 30 below are the ones people reach for most; your agent can call all 40. ### 30 of 40 Scale ai tools for OpenClaw | Tool | What it does | |---|---| | **Get assets** `scale_ai_get_assets` | Retrieve file assets with filtering capabilities by project and metadata | | **Get batch** `scale_ai_get_batch` | Retrieve the details of a batch with the specified name | | **Get batch status** `scale_ai_get_batch_status` | Retrieve the current status of a batch and task completion counts | | **Get fixless audits** `scale_ai_get_fixless_audits` | Retrieve fixless audits by task ID or audit ID | | **Get project** `scale_ai_get_project` | Retrieve details about a specific Scale AI project using its unique identifier | | **Get quality labelers** `scale_ai_get_quality_labelers` | Retrieve training attempts matching provided filter parameters | | **Get studio assignments** `scale_ai_get_studio_assignments` | Retrieve current project assignments of all active team users in Scale AI Studio | | **Get studio batches** `scale_ai_get_studio_batches` | Retrieve basic information about all pending batches in Studio | | **Get teams** `scale_ai_get_teams` | Retrieve basic information about all team members associated with the account | | **Get v1 task** `scale_ai_get_v1_task` | Retrieve detailed information about a specific task using its task ID | | **Get v1 task response URL** `scale_ai_get_v1_task_response_url` | Retrieve secure authenticated task response data | | **List batches** `scale_ai_list_batches` | Retrieve all batches in descending order by creation date | | **List projects** `scale_ai_list_projects` | Retrieve information for all projects in the Scale AI account with optional archived filtering | | **List tasks** `scale_ai_list_tasks` | Retrieve a paginated list of tasks in descending order by creation time | | **Add studio assignments** `scale_ai_add_studio_assignments` | Add project assignments to team members in Scale AI Studio | | **Add task tags** `scale_ai_add_task_tags` | Add tags to an existing task | | **Create batch** `scale_ai_create_batch` | Create a new batch within a project | | **Create document transcription task** `scale_ai_create_document_transcription_task` | Create a document transcription task where workers transcribe and annotate information from | | **Create image annotation task** `scale_ai_create_image_annotation_task` | Create an image annotation task where annotators label images with vector geometric shapes | | **Create lidar annotation task** `scale_ai_create_lidar_annotation_task` | Create a lidar annotation task where annotators mark objects with 3D cuboids in 3D space | | **Create lidar segmentation task** `scale_ai_create_lidar_segmentation_task` | Create a LiDAR segmentation task where annotators assign semantic class labels to individual | | **Create named entity recognition task** `scale_ai_create_named_entity_recognition_task` | Create a named entity recognition task for labelers to highlight text entity mentions | | **Create segmentation annotation task** `scale_ai_create_segmentation_annotation_task` | Create a segmentation task where annotators classify pixels in an image according to provided | | **Create text collection task** `scale_ai_create_text_collection_task` | Create a textcollection task for collecting information from attachments and/or web sources | | **Create video annotation task** `scale_ai_create_video_annotation_task` | Create a video annotation task where annotators draw geometric shapes around specified objects | | **Create video playback annotation task** `scale_ai_create_video_playback_annotation_task` | Create a video playback annotation task where annotators draw shapes around specified objects | | **Finalize batch** `scale_ai_finalize_batch` | Finalize a batch so its tasks can be worked on | | **Import file** `scale_ai_import_file` | Import files from an external URL endpoint into Scale's system rather than uploading directly | | **Invite team member** `scale_ai_invite_team_member` | Invite users by email to team with specified role | | **Post v1 task send callback** `scale_ai_post_v1_task_send_callback` | Re-send a callback for a completed or errored task to the callback_url | ## Example prompts **Get Assets** > Pull the relevant data from Scale ai, summarize it in plain English, and point out anything that needs attention. **Get Batch** > Pull the relevant data from Scale ai, summarize it in plain English, and point out anything that needs attention. **Get Batch Status** > Pull the relevant data from Scale ai, summarize it in plain English, and point out anything that needs attention. **Get Fixless Audits** > Pull the relevant data from Scale ai, 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 Scale ai working from chat. | | Manual | ClawLink | |---|---|---| | **Credential handling** | Collect, validate, store, and rotate the Scale ai API key yourself, then make sure every tool call uses the right account. | Users complete the hosted ClawLink setup once and the connected Scale ai 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 Scale ai. | 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 Scale ai actions to the runtime in a format your agent can reliably use. | 40 tools for Scale ai are already exposed through ClawLink, so the agent can read and act from chat immediately. | ## ClawLink vs. Composio Composio also exposes Scale ai 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 Scale ai in the browser, and the 40 tools above work from chat. There is no SDK and no config file, and the Scale ai 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 Scale ai skill but can't call the tools The ClawHub skill teaches OpenClaw about Scale ai, but the calls run through the ClawLink plugin and your connected account. Make sure Scale ai 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 Scale ai 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 Scale ai tools Scale ai 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 Scale ai 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. ### Scale ai 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 Scale ai has the right scopes or account access. A valid key can still be too limited for some reads or writes. ### Is there a OpenClaw Scale ai integration? Yes. ClawLink is the fastest way to connect OpenClaw to Scale ai: link your Scale ai account once in the browser and OpenClaw can call the Scale ai API through 40 ready-made tools — no custom code or token handling. ### How do I add Scale ai to OpenClaw with ClawLink? Paste the setup prompt from this page into OpenClaw. It installs the ClawLink Scale ai skill from ClawHub, then you click Connect in the dashboard to authorize Scale ai. OpenClaw calls the tools from the next message — no config files, and the Scale ai key you paste is stored server-side instead of in your environment. ### How long does it take to connect Scale ai to OpenClaw? About two minutes. Sign in, click Connect next to Scale ai in the dashboard, authenticate, and OpenClaw can use it from the next chat message. ### Why use ClawLink instead of wiring Scale ai 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 Scale ai working from chat. ### OpenClaw installed the Scale ai skill but can't call the tools The ClawHub skill teaches OpenClaw about Scale ai, but the calls run through the ClawLink plugin and your connected account. Make sure Scale ai 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 - [DataRobot tools](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. - [Connect Chatbotkit](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. - [Just One API](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.