# How to connect DataRobot to Hermes Agent (paste one key, 836 tools) > Connect DataRobot to Hermes with ClawLink: paste your DataRobot key once and 836 tools work from chat. No MCP server to run, nothing stored on your machine. Web version: https://claw-link.dev/hermes/datarobot Most guides for giving Hermes Agent DataRobot access start with registering your own OAuth app or pasting API keys into env files, then leave the token refresh and tool wiring to you. ClawLink gives Hermes a more practical DataRobot setup: pair once in the browser and your always-on Hermes agent can act on DataRobot for you, reading and doing real work on your behalf with no auth, token refresh, or tool wiring to build yourself. **Start here — paste this into Hermes to set up ClawLink:** > Set up ClawLink for Hermes and tell me when it's ready. > 1. Install the plugin: `hermes plugins install ClawLink-HQ/hermes-plugin --enable` > 2. Start pairing with `hermes clawlink begin`. It prints an approval link, so show me the link and stop, don't wait. > 3. I'll approve it in my browser, then reply "approved". > 4. When I say approved, finish setup: `hermes clawlink finish` > 5. Then run `hermes clawlink test` and tell me whether ClawLink is ready. ## Setup It takes three steps to connect Hermes to DataRobot. 1. **Install ClawLink** — add the plugin to Hermes Agent once. 2. **Connect DataRobot** — one-click OAuth in the ClawLink dashboard. 3. **Use it from chat** — ask Hermes Agent in plain English. **Alternative for any agent (no plugin needed):** if the Hermes Agent 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 datarobot # connect DataRobot (browser OAuth) npx -y @useclawlink/cli actions datarobot # list available actions npx -y @useclawlink/cli run datarobot --input '' # execute (add --confirm for writes) ``` ### Install by command The prompt above walks Hermes through this. By hand, it is four commands and a browser approval: ```bash hermes plugins install ClawLink-HQ/hermes-plugin --enable hermes clawlink begin # prints an approval link — open it and approve hermes clawlink finish # after approving in the browser hermes clawlink test ``` Then connect DataRobot in the [ClawLink dashboard](https://claw-link.dev/dashboard) — paste your DataRobot API key once. Verify the connection by asking Hermes: > Use DataRobot to add user to organization and walk me through the result in plain English. ### Using a different agent? The Hermes 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 DataRobot is connected in the dashboard, that agent calls the same 836 DataRobot 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). ## DataRobot MCP for Hermes Looking for a DataRobot MCP server for Hermes Agent? ClawLink connects DataRobot to Hermes Agent and exposes 836 DataRobot 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 OpenClaw instead? The [OpenClaw DataRobot integration](https://claw-link.dev/openclaw/datarobot) works the same way. ## What the Hermes Agent DataRobot integration can do 836 DataRobot tools are ready for Hermes Agent once the account is connected. The 30 below are the ones people reach for most; your agent can call all 836. ### 30 of 836 DataRobot tools for Hermes | Tool | What it does | |---|---| | **Add user to organization** `datarobot_add_user_to_organization` | Add a user to an existing organization | | **Add users to group** `datarobot_add_users_to_group` | Add one or more users to a DataRobot user group by groupId | | **Analyze dataset definition** `datarobot_analyze_dataset_definition` | Analyze a dataset definition by ID | | **Archive model package** `datarobot_archive_model_package` | Archive a DataRobot model package | | **Check project status** `datarobot_check_project_status` | Check the status of a DataRobot project | | **Create code snippets** `datarobot_create_code_snippets` | Generate code snippets for DataRobot models, predictions, or workloads | | **Create code snippets download** `datarobot_create_code_snippets_download` | Download code snippets for DataRobot deployments, models, or workloads | | **Create data slices slice sizes** `datarobot_create_data_slices_slice_sizes` | Compute the number of rows available after applying a data slice to a dataset subset | | **Create deployments actuals data exports** `datarobot_create_deployments_actuals_data_exports` | Create a deployment actuals data export for a specified time period | | **Create deployments training data exports** `datarobot_create_deployments_training_data_exports` | Create a deployment training data export in DataRobot | | **Create external data stores columns** `datarobot_create_external_data_stores_columns` | Retrieve column metadata from an external data store | | **Create external data stores columns info** `datarobot_create_external_data_stores_columns_info` | Retrieve column metadata for a table in an external data store | | **Create external data stores schemas** `datarobot_create_external_data_stores_schemas` | Retrieve data store schemas | | **Create external data stores tables** `datarobot_create_external_data_stores_tables` | Retrieve database tables and views from a DataRobot external data store | | **Create files links** `datarobot_create_files_links` | Generate temporary download URLs for files in a catalog item | | **Create files versions links** `datarobot_create_files_versions_links` | Generate temporary download URLs for catalog file versions | | **Create otel metrics values over time segments** `datarobot_create_otel_metrics_values_over_time_segments` | Get OpenTelemetry metric values for a specified entity, grouped by multiple attributes | | **Create projects cross series properties** `datarobot_create_projects_cross_series_properties` | Validate columns for potential use as the group-by column for cross-series functionality in a | | **Create recipes SQL** `datarobot_create_recipes_sql` | Build SQL query for a DataRobot recipe | | **Create string encryptions** `datarobot_create_string_encryptions` | Encrypt a string which DataRobot can decrypt when needed | | **Create usage data exports** `datarobot_create_usage_data_exports` | Create a customer usage data artifact request in DataRobot | | **Create user blueprints bulk validations** `datarobot_create_user_blueprints_bulk_validations` | Validate multiple user blueprints in bulk and check their configuration correctness | | **Create user blueprints task parameters** `datarobot_create_user_blueprints_task_parameters` | Validate task parameters for custom tasks in DataRobot User Blueprints | | **Download custom model** `datarobot_download_custom_model` | Download the latest custom model version content from DataRobot | | **Download custom model version** `datarobot_download_custom_model_version` | Download custom model version content from DataRobot as a file archive | | **Download file** `datarobot_download_file` | Download file data from a DataRobot catalog item by streaming it | | **Download scoring code** `datarobot_download_scoring_code` | Download scoring code for a DataRobot deployment | | **Evaluate entitlements** `datarobot_evaluate_entitlements` | Evaluate which entitlements are enabled for the authenticated user's DataRobot account | | **Export tenant usage** `datarobot_export_tenant_usage` | Export tenant resource usage data for billing and cost analysis | | **Get access role** `datarobot_get_access_role` | Retrieve details for a specific Access Role by ID | ## Example prompts **Add User To Organization** > Use DataRobot to add user to organization and walk me through the result in plain English. **Add Users To Group** > Use DataRobot to add users to group and walk me through the result in plain English. **Analyze Dataset Definition** > Use DataRobot to analyze dataset definition and walk me through the result in plain English. **Archive Model Package** > Before using DataRobot to archive model package, show me what will change and ask for confirmation. ## 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 Hermes Agent. That is fine if you want to build and maintain the integration yourself. Most teams just want DataRobot working from chat. | | Manual | ClawLink | |---|---|---| | **Credential handling** | Collect, validate, store, and rotate the DataRobot API key yourself, then make sure every tool call uses the right account. | Users complete the hosted ClawLink setup once and the connected DataRobot 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 DataRobot. | 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 DataRobot actions to the runtime in a format your agent can reliably use. | 836 tools for DataRobot are already exposed through ClawLink, so the agent can read and act from chat immediately. | ## ClawLink vs. Composio Composio also exposes DataRobot 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 Hermes Agent users instead. You install the plugin once, connect DataRobot in the browser, and the 836 tools above work from chat. There is no SDK and no config file, and the DataRobot 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. ### Hermes paired but still can't use DataRobot Pairing is a two-step handshake: run `hermes clawlink begin`, approve the link in your browser, then run `hermes clawlink finish`. If you ran finish before approving, or the approval link expired, run `hermes clawlink begin` again to get a fresh link. Confirm the plugin was installed with `--enable`, then verify with `hermes clawlink test`. ### Connection succeeds but no tools appear Reconnect DataRobot 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 DataRobot tools DataRobot 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 DataRobot 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. ### DataRobot 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 DataRobot has the right scopes or account access. A valid key can still be too limited for some reads or writes. ### Is there a Hermes Agent DataRobot integration? Yes. ClawLink is the fastest way to connect Hermes to DataRobot: link your DataRobot account once in the browser and Hermes Agent can call the DataRobot API through 836 ready-made tools — no custom code or token handling. ### How do I connect DataRobot to Hermes with ClawLink? Install the plugin with `hermes plugins install ClawLink-HQ/hermes-plugin --enable`, then pair once: run `hermes clawlink begin`, approve the link in your browser, and run `hermes clawlink finish`. Connect DataRobot in the dashboard and Hermes can use it from the next message — no config files, and the DataRobot key you paste is stored server-side instead of in your environment. ### How long does it take to connect DataRobot to Hermes Agent? About two minutes. Sign in, click Connect next to DataRobot in the dashboard, authenticate, and Hermes Agent can use it from the next chat message. ### Why use ClawLink instead of wiring DataRobot up myself? The alternative to ClawLink is usually manual API key setup plus your own token handling, permission troubleshooting, and tool plumbing for Hermes Agent. That is fine if you want to build and maintain the integration yourself. Most teams just want DataRobot working from chat. ### Hermes paired but still can't use DataRobot Pairing is a two-step handshake: run `hermes clawlink begin`, approve the link in your browser, then run `hermes clawlink finish`. If you ran finish before approving, or the approval link expired, run `hermes clawlink begin` again to get a fresh link. Confirm the plugin was installed with `--enable`, then verify with `hermes clawlink test`. ## Related - [Chatbotkit](https://claw-link.dev/hermes/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. - [ElevenLabs](https://claw-link.dev/hermes/elevenlabs) — Generate speech and voice cloning - [Griptape](https://claw-link.dev/hermes/griptape) — Griptape is a comprehensive platform offering tools and frameworks for building, deploying, and scaling generative AI applications.