# How to connect Chatbotkit to OpenClaw (paste one key, 284 tools) > Connect Chatbotkit to OpenClaw with ClawLink: paste your Chatbotkit key once and 284 tools work from chat. No MCP server to run, nothing stored on your machine. Web version: https://claw-link.dev/openclaw/chatbotkit The usual route to Chatbotkit 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 Chatbotkit setup: install one ClawHub skill, connect Chatbotkit in the browser, and OpenClaw can call real Chatbotkit actions from any chat surface with no auth, token refresh, or tool wiring to build yourself. **Start here:** install the ClawLink plugin (`openclaw plugins install clawhub:clawlink-plugin`), pair it in the browser, then connect the app in the ClawLink dashboard. The interactive install prompt is on the web version of this page: https://claw-link.dev/openclaw/chatbotkit ## Setup It takes three steps to connect OpenClaw to Chatbotkit. 1. **Install ClawLink** — add the plugin to OpenClaw once. 2. **Connect Chatbotkit** — one-click OAuth in the ClawLink dashboard. 3. **Use it from chat** — ask OpenClaw in plain English. **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 chatbotkit # connect Chatbotkit (browser OAuth) npx -y @useclawlink/cli actions chatbotkit # list available actions npx -y @useclawlink/cli run chatbotkit --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 Chatbotkit in the [ClawLink dashboard](https://claw-link.dev/dashboard) — paste your Chatbotkit API key once. Verify the connection by asking OpenClaw: > Use Chatbotkit to attach dataset file 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 Chatbotkit is connected in the dashboard, that agent calls the same 284 Chatbotkit 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). ## Chatbotkit MCP for OpenClaw Looking for a Chatbotkit MCP server for OpenClaw? ClawLink connects Chatbotkit to OpenClaw and exposes 284 Chatbotkit 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 Chatbotkit integration](https://claw-link.dev/hermes/chatbotkit) works the same way. ## What the OpenClaw Chatbotkit integration can do 284 Chatbotkit 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 284. ### 30 of 284 Chatbotkit tools for OpenClaw | Tool | What it does | |---|---| | **Attach dataset file** `chatbotkit_attach_dataset_file` | Attach a file to a dataset as a source | | **Authenticate secret** `chatbotkit_authenticate_secret` | Authenticate a secret by its ID | | **Clone blueprint** `chatbotkit_clone_blueprint` | Clone an existing blueprint | | **Clone bot** `chatbotkit_clone_bot` | Clone an existing bot | | **Download file** `chatbotkit_download_file` | Download a file by its ID | | **Export contacts** `chatbotkit_export_contacts` | Export contacts with pagination support | | **Export conversations** `chatbotkit_export_conversations` | Export conversations with pagination support | | **Export dataset records** `chatbotkit_export_dataset_records` | Export dataset records with pagination support | | **Export event logs** `chatbotkit_export_event_logs` | Export event logs with pagination support | | **Export memories** `chatbotkit_export_memories` | Export memories with pagination support | | **Export skillset abilities** `chatbotkit_export_skillset_abilities` | Export all abilities from a specific skillset with pagination support | | **Export spaces** `chatbotkit_export_spaces` | Export spaces with pagination support | | **Export tasks** `chatbotkit_export_tasks` | Export tasks with pagination support | | **Fetch blueprint** `chatbotkit_fetch_blueprint` | Fetch a blueprint by ID | | **Fetch blueprint graphql** `chatbotkit_fetch_blueprint_graphql` | Fetch a single blueprint by ID using GraphQL | | **Fetch bot** `chatbotkit_fetch_bot` | Fetch a specific bot by its ID | | **Fetch bot graphql** `chatbotkit_fetch_bot_graphql` | Fetch a single bot by ID using GraphQL query | | **Fetch bot usage** `chatbotkit_fetch_bot_usage` | Fetch bot usage statistics for a specific bot | | **Fetch contact** `chatbotkit_fetch_contact` | Retrieve detailed information about a specific contact by ID | | **Fetch conversation** `chatbotkit_fetch_conversation` | Retrieve full details of a specific conversation by its ID | | **Fetch conversation message** `chatbotkit_fetch_conversation_message` | Retrieve full details of a specific message within a conversation | | **Fetch conversation usage** `chatbotkit_fetch_conversation_usage` | Fetch usage statistics for a specific conversation | | **Fetch conversation with messages graphql** `chatbotkit_fetch_conversation_with_messages_graphql` | Fetch a single conversation by ID with messages and metadata using GraphQL | | **Fetch dataset** `chatbotkit_fetch_dataset` | Fetch a specific dataset by its ID | | **Fetch dataset graphql** `chatbotkit_fetch_dataset_graphql` | Fetch a single dataset by ID using GraphQL | | **Fetch dataset record** `chatbotkit_fetch_dataset_record` | Fetch a specific record from a dataset by its ID | | **Fetch discord integration** `chatbotkit_fetch_discord_integration` | Fetch a specific Discord integration by its ID | | **Fetch email integration** `chatbotkit_fetch_email_integration` | Fetch a specific Email integration by its ID | | **Fetch extract integration** `chatbotkit_fetch_extract_integration` | Fetch a specific Extract integration by its ID | | **Fetch file** `chatbotkit_fetch_file` | Retrieve detailed metadata about a specific file by its ID | ## Example prompts **Attach Dataset File** > Use Chatbotkit to attach dataset file and walk me through the result in plain English. **Authenticate Secret** > Use Chatbotkit to authenticate secret and walk me through the result in plain English. **Clone Blueprint** > Use Chatbotkit to clone blueprint and walk me through the result in plain English. **Clone Bot** > Use Chatbotkit to clone bot 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 OpenClaw. That is fine if you want to build and maintain the integration yourself. Most teams just want Chatbotkit working from chat. | | Manual | ClawLink | |---|---|---| | **Credential handling** | Collect, validate, store, and rotate the Chatbotkit API key yourself, then make sure every tool call uses the right account. | Users complete the hosted ClawLink setup once and the connected Chatbotkit 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 Chatbotkit. | 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 Chatbotkit actions to the runtime in a format your agent can reliably use. | 284 tools for Chatbotkit are already exposed through ClawLink, so the agent can read and act from chat immediately. | ## ClawLink vs. Composio Composio also exposes Chatbotkit 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 Chatbotkit in the browser, and the 284 tools above work from chat. There is no SDK and no config file, and the Chatbotkit 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 Chatbotkit skill but can't call the tools The ClawHub skill teaches OpenClaw about Chatbotkit, but the calls run through the ClawLink plugin and your connected account. Make sure Chatbotkit 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 Chatbotkit 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 Chatbotkit tools Chatbotkit 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 Chatbotkit 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. ### Chatbotkit 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 Chatbotkit has the right scopes or account access. A valid key can still be too limited for some reads or writes. ### Is there a OpenClaw Chatbotkit integration? Yes. ClawLink is the fastest way to connect OpenClaw to Chatbotkit: link your Chatbotkit account once in the browser and OpenClaw can call the Chatbotkit API through 284 ready-made tools — no custom code or token handling. ### How do I add Chatbotkit to OpenClaw with ClawLink? Paste the setup prompt from this page into OpenClaw. It installs the ClawLink Chatbotkit skill from ClawHub, then you click Connect in the dashboard to authorize Chatbotkit. OpenClaw calls the tools from the next message — no config files, and the Chatbotkit key you paste is stored server-side instead of in your environment. ### How long does it take to connect Chatbotkit to OpenClaw? About two minutes. Sign in, click Connect next to Chatbotkit in the dashboard, authenticate, and OpenClaw can use it from the next chat message. ### Why use ClawLink instead of wiring Chatbotkit 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 Chatbotkit working from chat. ### OpenClaw installed the Chatbotkit skill but can't call the tools The ClawHub skill teaches OpenClaw about Chatbotkit, but the calls run through the ClawLink plugin and your connected account. Make sure Chatbotkit 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 - [Connect DataRobot](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 ElevenLabs](https://claw-link.dev/openclaw/elevenlabs) — Generate speech and voice cloning - [Griptape tools](https://claw-link.dev/openclaw/griptape) — Griptape is a comprehensive platform offering tools and frameworks for building, deploying, and scaling generative AI applications.