--- title: "Connect Airbrake to Keywords AI - APIANT.ai" description: "When \"New error\" fires in Airbrake, your agent runs \"Update user\" in Keywords AI." canonical: "https://apiant.ai/connect/airbrake-to-keywords-ai" --- # Connect Airbrake to Keywords AI When **New error** fires in [Airbrake](https://apiant.ai/connections/airbrake), your agent runs **Update user** in [Keywords AI](https://apiant.ai/connections/keywords-ai). Describe the whole flow and it is built, tested on every scenario and kept running. Airbrake **1** trigger Airbrake **14** actions Keywords AI **16** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want Airbrake and Keywords AI to do together? Give your AI client this address. `https://mcp.apiant.ai` One connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser. ### Set it up in your client ### Claude Code Run this in the directory you want to work in. `claude mcp add --transport http -s project apiant-ai https://mcp.apiant.ai` Start Claude Code there, approve the server, and sign in in the browser page it opens. [Claude Code guide (opens in a new tab)](https://apiant.ai/docs/mcp/claude-code) ### Claude, web and desktop Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) ### Cursor Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) ### Zed Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) ### Codex and the ChatGPT desktop app Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) ### Any other MCP client Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) Example flows ## What Airbrake can start in Keywords AI - When **New error** in Airbrake then **Update user** in Keywords AI - When **New error** in Airbrake then **Add prompt** in Keywords AI Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships. Everything your agent can do with Airbrake and Keywords AI ## Triggers and actions 1 trigger · 30 actions - Trigger **New error** Triggered when any new error is reported. - Action **Create notice** Submit a new error notice to Airbrake — report an error from an automation. - Action **Delete error group** Delete/resolve an Airbrake error group by id. - Action **Get error group** Fetch details for a single error group. - Action **Get project** Fetch details for a single project by ID. - Action **List activities** List the audit-log activities for an Airbrake project — deploys, mutes, resolves, etc. - Action **List deploys** List recorded deploys for an Airbrake project. - Action **List error groups** List error groups (aggregated errors) for a project. - Action **List notices** List individual notices (occurrences) for an error group. - Action **List projects** List all projects accessible to the authenticated user key. - Action **List source maps** List the uploaded source maps for an Airbrake project. - Action **Mute error group** Mute an error group so it no longer triggers notifications. - Action **Record deploy** Record a new deployment for a project (environment, revision, version, etc.). - Action **Show deploy** Retrieve a single Airbrake deploy by id. - Action **Unmute error group** Unmute a previously muted error group to re-enable notifications. - Action **Add prompt** Creates a new prompt in your Keywords AI workspace with an optional description. Returns the new prompt, including its id and slug. - Action **Add prompt version** Creates a new version of a prompt with its messages, model and settings. The new version becomes the prompt's current draft and earlier versions become read-only. - Action **Add span** Logs an LLM call or workflow step as a span in Keywords AI (Respan), with its model, input, output, token usage, latency and trace links. Returns the stored span. - Action **Delete prompt** Deletes a prompt and all of its versions from your prompt library. - Action **Get prompt** Returns a prompt template with its name, description, slug, tags, and its current and deployed (live) versions. - Action **Get span** Returns a single span (logged LLM request) with its input, output, token usage, cost, latency, metadata and evaluation scores. - Action **Get trace** Returns one trace with its aggregate cost, token and error metrics and its full tree of spans. - Action **Get user** Returns a user's profile and current budget usage, looked up by your own identifier for that user. - Action **List models** Returns the models your Keywords AI project can use through the gateway, with each model's context window and pricing. - Action **List prompts** Returns the prompts in your Keywords AI workspace, optionally filtered and sorted. - Action **List prompt versions** Returns every version of a prompt, newest first, including each version's messages, model and settings. - Action **List spans** Returns the spans (request logs) in your Keywords AI account, optionally filtered by time range, environment, type and span fields, and sorted as you choose. - Action **List traces** Returns the traces recorded in your Keywords AI account, optionally narrowed by time range, environment and filter conditions. - Action **List users** Returns the users (your end customers) tracked in your organization, with their usage analytics such as requests, tokens, cost and budget settings. - Action **Update prompt** Updates the name or description of a prompt in Keywords AI. - Action **Update user** Updates a user's profile and spending budget in Keywords AI, such as their name, email, metadata, budgets and markup. Returns the updated user. ## Each app on its own - [ **Airbrake** Airbrake collects errors generated by other applications, and aggregates the results for review.](https://apiant.ai/connections/airbrake) - [ **Keywords AI** Keywords AI is an LLM observability and gateway platform for tracking, debugging, and managing AI workflows...](https://apiant.ai/connections/keywords-ai) Reviews ## What our customers say ## More from Airbrake - [ **Airbrake to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/airbrake-to-hubspot) - [ **Airbrake to Stripe** Stripe is a payment processing platform for online businesses.](https://apiant.ai/connect/airbrake-to-stripe) - [ **Airbrake to QuickBooks Online** QuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...](https://apiant.ai/connect/airbrake-to-quickbooks-online) - [ **Airbrake to Pipedrive** Pipedrive is a sales CRM and pipeline management tool.](https://apiant.ai/connect/airbrake-to-pipedrive) - [ **Airbrake to Asana** Asana is a collaborative information manager for workspace.](https://apiant.ai/connect/airbrake-to-asana) - [ **Airbrake to JIRA** Atlassian JIRA Cloud — issue tracking and project management.](https://apiant.ai/connect/airbrake-to-jira) ## More into Keywords AI - [ **HubSpot to Keywords AI** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-keywords-ai) - [ **Salesforce to Keywords AI** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-keywords-ai) - [ **Slack to Keywords AI** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-keywords-ai) - [ **Google Sheets to Keywords AI** Google Sheets](https://apiant.ai/connect/google-sheets-to-keywords-ai) - [ **Gmail to Keywords AI** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-keywords-ai) - [ **Google Calendar to Keywords AI** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-keywords-ai) Questions ## Airbrake and Keywords AI, answered ### ### What can start an automation from Airbrake? Any of Airbrake's 1 trigger in the catalog, including New error. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Keywords AI when something happens in Airbrake? Any of Keywords AI's 16 actions, including Update prompt, Update user, Add prompt and Add prompt version. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Keywords AI to Airbrake? Keywords AI has no triggers in the catalog today, so automations start in Airbrake. If you need the other direction, ask: your agent reads Keywords AI's API documentation and adds it. ### ### Do I have to build a connector for Airbrake or Keywords AI? No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running. ### ### Can my AI client use Airbrake and Keywords AI without building an automation? Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both. ### ### What happens when something fails? Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships. ### ### Is there a free plan? Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.