# How to connect Kaggle to Hermes Agent (paste one key, 35 tools) > Connect Kaggle to Hermes with ClawLink: paste your Kaggle key once and 35 tools work from chat. No MCP server to run, nothing stored on your machine. Web version: https://claw-link.dev/hermes/kaggle Most guides for giving Hermes Agent Kaggle 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 Kaggle setup: pair once in the browser and your always-on Hermes agent can act on Kaggle for you, reading and doing real work on your behalf with no auth, token refresh, or tool wiring to build yourself. ## Setup It takes three steps to connect Hermes to Kaggle. 1. **Install ClawLink** — add the plugin to Hermes Agent once. 2. **Connect Kaggle** — one-click OAuth in the ClawLink dashboard. 3. **Use it from chat** — ask Hermes Agent in plain English. **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. **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 kaggle # connect Kaggle (browser OAuth) npx -y @useclawlink/cli actions kaggle # list available actions npx -y @useclawlink/cli run kaggle --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 Kaggle in the [ClawLink dashboard](https://claw-link.dev/dashboard) — paste your Kaggle API key once. Verify the connection by asking Hermes: > Use Kaggle to competition download files 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 Kaggle is connected in the dashboard, that agent calls the same 35 Kaggle 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). ## Kaggle MCP for Hermes Looking for a Kaggle MCP server for Hermes Agent? ClawLink connects Kaggle to Hermes Agent and exposes 35 Kaggle 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 Kaggle integration](https://claw-link.dev/openclaw/kaggle) works the same way. ## What the Hermes Agent Kaggle integration can do 35 Kaggle 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 35. ### 30 of 35 Kaggle tools for Hermes | Tool | What it does | |---|---| | **Competition download files** `kaggle_competition_download_files` | Downloads all data files for a Kaggle competition as a single zip archive | | **Config dir** `kaggle_config_dir` | Retrieve the directory of the Kaggle API configuration file | | **Config keys** `kaggle_config_keys` | List local Kaggle API configuration keys | | **Config path** `kaggle_config_path` | Retrieve local Kaggle API configuration file path | | **Config view** `kaggle_config_view` | View local Kaggle API credentials and configuration settings | | **Dataset list files** `kaggle_dataset_list_files` | List files in a Kaggle dataset | | **Dataset status** `kaggle_dataset_status` | Check the processing status of a Kaggle dataset after creation or version update | | **Download competition file** `kaggle_download_competition_file` | Download a specific data file from a Kaggle competition | | **Download competition leaderboard** `kaggle_download_competition_leaderboard` | Download the entire competition leaderboard as a CSV file packaged in a ZIP archive | | **Download dataset** `kaggle_download_dataset` | Download all files from a Kaggle dataset as a zip archive | | **Download dataset file** `kaggle_download_dataset_file` | Download a specific file from a Kaggle dataset | | **Get dataset metadata** `kaggle_get_dataset_metadata` | Get comprehensive metadata for a Kaggle dataset including title, description, licenses, and tags | | **Get model** `kaggle_get_model` | Get a Kaggle model's details including metadata and description | | **Get model instance** `kaggle_get_model_instance` | Get details for a specific Kaggle model instance (variation) | | **Kernel output** `kaggle_kernel_output` | Download the output of a Kaggle kernel | | **Kernels status** `kaggle_kernels_status` | Get the execution status of a Kaggle kernel (notebook) | | **List competition files** `kaggle_list_competition_files` | List all data files available for a Kaggle competition | | **List competitions** `kaggle_list_competitions` | List available Kaggle competitions with filters and pagination | | **List datasets** `kaggle_list_datasets` | List Kaggle datasets with filters and pagination | | **List kernel output files** `kaggle_list_kernel_output_files` | List output files for a specific kernel run | | **List kernels** `kaggle_list_kernels` | List Kaggle kernels (notebooks and scripts) with filters and pagination | | **List model instance version files** `kaggle_list_model_instance_version_files` | List files for a specific version of a model variation | | **List models** `kaggle_list_models` | List Kaggle models with optional filters for owner, sorting, search, and pagination | | **Pull kernel** `kaggle_pull_kernel` | Pull (download) the source code of a Kaggle kernel to local storage | | **View competition leaderboard** `kaggle_view_competition_leaderboard` | View competition leaderboard information showing rankings and scores of participants | | **Competition submit** `kaggle_competition_submit` | Submit an entry to a Kaggle competition using a previously uploaded file | | **Config init** `kaggle_config_init` | Initialize Kaggle API client configuration | | **Config set** `kaggle_config_set` | Set a Kaggle CLI configuration parameter | | **Config unset** `kaggle_config_unset` | Unset a Kaggle CLI configuration parameter | | **Dataset create** `kaggle_dataset_create` | Create a new Kaggle dataset with metadata | ## Example prompts **Competition Download Files** > Use Kaggle to competition download files and walk me through the result in plain English. **Config Dir** > Use Kaggle to config dir and walk me through the result in plain English. **Config Keys** > Use Kaggle to config keys and walk me through the result in plain English. **Config Path** > Use Kaggle to config path and walk me through the result in plain English. ## 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 Kaggle working from chat. | | Manual | ClawLink | |---|---|---| | **Credential handling** | Collect, validate, store, and rotate the Kaggle API key yourself, then make sure every tool call uses the right account. | Users complete the hosted ClawLink setup once and the connected Kaggle 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 Kaggle. | 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 Kaggle actions to the runtime in a format your agent can reliably use. | 35 tools for Kaggle are already exposed through ClawLink, so the agent can read and act from chat immediately. | ## ClawLink vs. Composio Composio also exposes Kaggle 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 Kaggle in the browser, and the 35 tools above work from chat. There is no SDK and no config file, and the Kaggle 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 Kaggle 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 Kaggle 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 Kaggle tools Kaggle 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 Kaggle 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. ### Kaggle 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 Kaggle 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 Kaggle integration? Yes. ClawLink is the fastest way to connect Hermes to Kaggle: link your Kaggle account once in the browser and Hermes Agent can call the Kaggle API through 35 ready-made tools — no custom code or token handling. ### How do I connect Kaggle 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 Kaggle in the dashboard and Hermes can use it from the next message — no config files, and the Kaggle key you paste is stored server-side instead of in your environment. ### How long does it take to connect Kaggle to Hermes Agent? About two minutes. Sign in, click Connect next to Kaggle in the dashboard, authenticate, and Hermes Agent can use it from the next chat message. ### Why use ClawLink instead of wiring Kaggle 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 Kaggle working from chat. ### Hermes paired but still can't use Kaggle 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 - [Connect DataRobot](https://claw-link.dev/hermes/datarobot) — DataRobot is a machine learning platform that automates model building, deployment, and monitoring, enabling organizations to derive predictive insights from large datasets. - [Hermes Chatbotkit integration](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. - [Connect Just One API](https://claw-link.dev/hermes/just-one-api) — Just One API provides unified access to public social media, creator, entertainment, and ecommerce data across hundreds of metered endpoints.