# Connect Bart and Openlayer When **New service advisory** fires in [Bart](https://apiant.ai/connections/bart), your agent runs **Publish Record** in [Openlayer](https://apiant.ai/connections/openlayer), or **New Project** in Openlayer to **Find trips by origin and destination** in Bart. Describe the whole flow and it is built, tested on every scenario and kept running. Bart **1** trigger Bart **8** actions Openlayer **2** triggers Openlayer **22** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want Bart and Openlayer to do together? Give your AI client this address. `https://mcp.apiant.ai` 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 Bart and Openlayer can do together ### From Bart to Openlayer - When **New service advisory** in Bart then **Publish Record** in Openlayer - When **New service advisory** in Bart then **Create Project** in Openlayer ### From Openlayer to Bart - When **New Project** in Openlayer then **Find trips by origin and destination** in Bart - When **New Test Result** in Openlayer then **Get route** in Bart 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 Bart and Openlayer ## Triggers and actions 3 triggers · 30 actions - Trigger **New service advisory** Triggers when BART posts a new service advisory (delay, emergency or information notice). - Action **Find trips by origin and destination** Finds BART trips departing from an origin station to a destination station around a given time, with fares and legs for each trip. - Action **Get route** Returns details for a BART route: its name, colour, origin and destination, and the ordered list of stations it serves. - Action **Get station** Returns detailed information about a BART station, including its address, location, routes, platforms and nearby attractions. - Action **Get station schedule** Returns the full day's scheduled train departures from a BART station, with line, destination, time and platform for each. - Action **List real-time departures** Returns the current estimated departure times for trains leaving a BART station, grouped by destination. - Action **List routes** Returns the list of BART routes (lines) in service for the current or a chosen schedule date. - Action **List service advisories** Returns BART's current service advisories (delays, emergencies and general information). - Action **List stations** Returns every BART station with its full name, abbreviation, coordinates and address. - Trigger **New Project** Triggers when a new project is created in your Openlayer workspace. - Trigger **New Test Result** Triggers when a new test result is available for a data source. Useful for alerting on passing or failing model tests. - Action **Create Data Source** Creates a new data source in a project for streaming production data to Openlayer. - Action **Create Project** Creates a new AI or ML project in your Openlayer workspace. - Action **Create Test** Creates a data quality test in a project. Checks for duplicate rows, null values, or row counts. - Action **Delete Inference Pipeline** Delete an inference pipeline by its ID. - Action **Delete Project** Delete a project by its ID. - Action **Delete Test** Delete a test by its ID. - Action **Evaluate Test** Evaluates a test for a specific time range. Use after publishing records to get immediate results. - Action **Find Data Source** Finds a data source (inference pipeline) by name in a project. - Action **Find Project** Finds a project by name in your Openlayer workspace. - Action **Find Test Result** Finds test results for a data source, including whether each test passed or failed. Filter by outcome or test type to branch an automation on the result. - Action **Get Inference Pipeline** Retrieve the details around a specific inference pipeline. - Action **Get Project** Retrieves one project by its id. Openlayer has no single-project endpoint, so this reads the workspace's first 100 projects and returns the one matching the id. - Action **Get Test** Retrieve a test by ID. - Action **Get Test Result** Retrieves one test result by its id. Openlayer has no single-result endpoint, so this reads the data source's 100 most recent results and returns the matching one. - Action **List Inference Pipelines** List the authenticated user's inference pipelines under a project. - Action **List Projects** Lists the projects in your Openlayer workspace, optionally narrowed to one kind of project. Returns up to 100 projects. - Action **List Test Results** List all results for a test/goal under an inference pipeline. - Action **List Tests** Lists the tests in a project, optionally narrowed by kind, archived state or monitoring mode. Returns up to 100 tests. - Action **Publish Record** Publishes an LLM inference record to a data source for monitoring. Streams the model input, output, and metadata to Openlayer. - Action **Update Inference Pipeline** Update an inference pipeline. - Action **Update Project** Update a project. - Action **Update Test** Update a test (partial updates allowed). ## Each app on its own - [ **Bart** Real-time BART (Bay Area Rapid Transit) train schedules, arrivals, and station data API.](https://apiant.ai/connections/bart) - [ **Openlayer** Openlayer is a platform for monitoring, evaluating, and testing AI and ML models in production.](https://apiant.ai/connections/openlayer) Reviews ## What our customers say ## More from Bart - [ **Bart to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/bart-to-hubspot) - [ **Bart to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/bart-to-salesforce) - [ **Bart to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/bart-to-slack) - [ **Bart to Google Sheets** Google Sheets](https://apiant.ai/connect/bart-to-google-sheets) - [ **Bart to Gmail** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/bart-to-gmail) - [ **Bart to Google Calendar** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/bart-to-google-calendar) ## More into Openlayer - [ **Google Sheets to Openlayer** Google Sheets](https://apiant.ai/connect/google-sheets-to-openlayer) - [ **Gmail to Openlayer** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-openlayer) - [ **Google Calendar to Openlayer** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-openlayer) - [ **Google Drive to Openlayer** Google Drive is a cloud storage solution for uploading, sharing, and collaborating on files across devices...](https://apiant.ai/connect/google-drive-to-openlayer) - [ **Mailchimp to Openlayer** Mailchimp marketing automation and email platform.](https://apiant.ai/connect/mailchimp-to-openlayer) - [ **ActiveCampaign to Openlayer** ActiveCampaign is a marketing automation, email marketing, and CRM platform.](https://apiant.ai/connect/activecampaign-to-openlayer) Questions ## Bart and Openlayer, answered ### ### What can start an automation from Bart? Any of Bart's 1 trigger in the catalog, including New service advisory. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Openlayer when something happens in Bart? Any of Openlayer's 22 actions, including Create Data Source, Create Project, Create Test and Update Inference Pipeline. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Openlayer to Bart? Yes. When something happens in Openlayer, your agent can act in Bart too. This page covers both directions: Openlayer's triggers and Bart's actions are listed here as well. ### ### Do I have to build a connector for Bart or Openlayer? 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. ### ### 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.