# How to connect Braintrust to OpenClaw (paste one key, 17 tools) > Connect Braintrust to OpenClaw with ClawLink: paste your Braintrust key once and 17 tools work from chat. No MCP server to run, nothing stored on your machine. Web version: https://claw-link.dev/openclaw/braintrust The usual route to Braintrust 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 Braintrust setup: install one ClawHub skill, connect Braintrust in the browser, and OpenClaw can call real Braintrust 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 Braintrust. 1. **Install ClawLink** — add the plugin to OpenClaw once. 2. **Connect Braintrust** — 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 braintrust # connect Braintrust (browser OAuth) npx -y @useclawlink/cli actions braintrust # list available actions npx -y @useclawlink/cli run braintrust --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 Braintrust in the [ClawLink dashboard](https://claw-link.dev/dashboard) — paste your Braintrust API key once. Verify the connection by asking OpenClaw: > Pull the relevant data from Braintrust, 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 Braintrust is connected in the dashboard, that agent calls the same 17 Braintrust 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). ## Braintrust MCP for OpenClaw Looking for a Braintrust MCP server for OpenClaw? ClawLink connects Braintrust to OpenClaw and exposes 17 Braintrust 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 Braintrust integration](https://claw-link.dev/hermes/braintrust) works the same way. ## What the OpenClaw Braintrust integration can do 17 Braintrust tools are ready for OpenClaw once the account is connected. The 15 below are the ones people reach for most; your agent can call all 17. ### 15 of 17 Braintrust tools for OpenClaw | Tool | What it does | |---|---| | **Fetch events** `braintrust_fetch_events` | Fetch one newest-to-oldest page of project log, experiment, or dataset events | | **Get resource** `braintrust_get_resource` | Get one project, experiment, dataset, prompt, or function by UUID | | **List resources** `braintrust_list_resources` | List and filter one page of projects, experiments, datasets, prompts, or functions visible to | | **Query data** `braintrust_query_data` | Run one bounded synchronous read-only BTQL query over Braintrust project logs, an experiment | | **Summarize resource** `braintrust_summarize_resource` | Return metadata and optional aggregate summaries for one Braintrust experiment or dataset | | **Create dataset** `braintrust_create_dataset` | Create a named dataset under a Braintrust project, or return the existing dataset unchanged | | **Create experiment** `braintrust_create_experiment` | Create an experiment under a Braintrust project | | **Create project** `braintrust_create_project` | Create a Braintrust project, or return the existing project unchanged when its name already | | **Create prompt** `braintrust_create_prompt` | Upsert a versioned prompt configuration under a Braintrust project without invoking it | | **Insert dataset events** `braintrust_insert_dataset_events` | Upsert a batch of examples into an existing Braintrust dataset | | **Insert experiment events** `braintrust_insert_experiment_events` | Upsert a batch of result events into an existing Braintrust experiment | | **Update dataset** `braintrust_update_dataset` | Update the name, description, tags, or metadata of a Braintrust dataset | | **Update experiment** `braintrust_update_experiment` | Update selected metadata and linkage fields on a Braintrust experiment | | **Update project** `braintrust_update_project` | Update selected fields of a Braintrust project | | **Update prompt** `braintrust_update_prompt` | Update a Braintrust prompt's metadata or configuration without invoking it | ## Example prompts **Fetch Events** > Pull the relevant data from Braintrust, summarize it in plain English, and point out anything that needs attention. **Get Resource** > Pull the relevant data from Braintrust, summarize it in plain English, and point out anything that needs attention. **List Resources** > List the relevant items in Braintrust, group them by priority, and recommend what OpenClaw should do next. **Query Data** > Use Braintrust to query data 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 Braintrust working from chat. | | Manual | ClawLink | |---|---|---| | **Credential handling** | Collect, validate, store, and rotate the Braintrust API key yourself, then make sure every tool call uses the right account. | Users complete the hosted ClawLink setup once and the connected Braintrust 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 Braintrust. | 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 Braintrust actions to the runtime in a format your agent can reliably use. | 17 tools for Braintrust are already exposed through ClawLink, so the agent can read and act from chat immediately. | ## ClawLink vs. Composio Composio also exposes Braintrust 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 Braintrust in the browser, and the 17 tools above work from chat. There is no SDK and no config file, and the Braintrust 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 Braintrust skill but can't call the tools The ClawHub skill teaches OpenClaw about Braintrust, but the calls run through the ClawLink plugin and your connected account. Make sure Braintrust 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 Braintrust 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 Braintrust tools Braintrust 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 Braintrust 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. ### Braintrust 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 Braintrust has the right scopes or account access. A valid key can still be too limited for some reads or writes. ### Is there a OpenClaw Braintrust integration? Yes. ClawLink is the fastest way to connect OpenClaw to Braintrust: link your Braintrust account once in the browser and OpenClaw can call the Braintrust API through 17 ready-made tools — no custom code or token handling. ### How do I add Braintrust to OpenClaw with ClawLink? Paste the setup prompt from this page into OpenClaw. It installs the ClawLink Braintrust skill from ClawHub, then you click Connect in the dashboard to authorize Braintrust. OpenClaw calls the tools from the next message — no config files, and the Braintrust key you paste is stored server-side instead of in your environment. ### How long does it take to connect Braintrust to OpenClaw? About two minutes. Sign in, click Connect next to Braintrust in the dashboard, authenticate, and OpenClaw can use it from the next chat message. ### Why use ClawLink instead of wiring Braintrust 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 Braintrust working from chat. ### OpenClaw installed the Braintrust skill but can't call the tools The ClawHub skill teaches OpenClaw about Braintrust, but the calls run through the ClawLink plugin and your connected account. Make sure Braintrust 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. - [OpenClaw Chatbotkit integration](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.