--- title: "Connect Openlayer to Tavily - APIANT.ai" description: "When \"New Project\" fires in Openlayer, your agent runs \"Create research task\" in Tavily." canonical: "https://apiant.ai/connect/openlayer-to-tavily" --- # Connect Openlayer to Tavily When **New Project** fires in [Openlayer](https://apiant.ai/connections/openlayer), your agent runs **Create research task** in [Tavily](https://apiant.ai/connections/tavily). Describe the whole flow and it is built, tested on every scenario and kept running. Openlayer **2** triggers Openlayer **22** actions Tavily **7** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want Openlayer and Tavily 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 Openlayer can start in Tavily - When **New Project** in Openlayer then **Create research task** in Tavily - When **New Test Result** in Openlayer then **Get research task status** in Tavily 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 Openlayer and Tavily ## Triggers and actions 2 triggers · 29 actions - 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). - Action **Crawl** Crawls a website starting from one address and returns the content of the pages it finds. - Action **Create research task** Starts a Tavily research task for a question you supply and returns its ID and status. Use the ID with Get research task status to collect the finished report. - Action **Extract** Reads one or more web pages and returns their content as markdown or plain text, plus any addresses that could not be read. - Action **Get research task status** Checks a Tavily research task by its ID and returns its current status, and the finished report with its sources once the task is complete. - Action **Get usage** Returns how many Tavily credits have been used this billing cycle, for both the API key and the account, along with the plan limits and a breakdown per feature. - Action **Map** Maps a website starting from an address you supply and returns the list of pages found, without pulling their content. - Action **Search** Searches the web for a query you supply and returns ranked results with titles, addresses and snippets, plus an optional written answer. ## Each app on its own - [ **Openlayer** Openlayer is a platform for monitoring, evaluating, and testing AI and ML models in production.](https://apiant.ai/connections/openlayer) - [ **Tavily** Tavily AI is a web research tool optimized for LLMs and RAG, offering access to real-time, reliable online...](https://apiant.ai/connections/tavily) Reviews ## What our customers say ## More from Openlayer - [ **Openlayer to Astroworld** Astroworld serves reference data about the game Minecraft.](https://apiant.ai/connect/openlayer-to-astroworld) - [ **Openlayer to Byabbe** Seach histories from wikipedia for a particular day](https://apiant.ai/connect/openlayer-to-byabbe) - [ **Openlayer to Cliniko** Cliniko is a practice management platform — manage patients, appointments, invoices, contacts, and...](https://apiant.ai/connect/openlayer-to-cliniko) - [ **Openlayer to Enrich CRM** Enrich CRM helps you perform real-time contact and company enrichment.](https://apiant.ai/connect/openlayer-to-enrich-crm) - [ **Openlayer to Evervault** Evervault provides secure encryption infrastructure for developers.](https://apiant.ai/connect/openlayer-to-evervault) - [ **Openlayer to Postman** Postman is a platform for building and testing APIs.](https://apiant.ai/connect/openlayer-to-postman) ## More into Tavily - [ **CRUSH to Tavily** CRUSH is an AI powered second brain helping you collect a thought, organize it and take action.](https://apiant.ai/connect/crush-to-tavily) - [ **HubSpot to Tavily** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-tavily) - [ **Salesforce to Tavily** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-tavily) - [ **Slack to Tavily** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-tavily) - [ **Google Sheets to Tavily** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-tavily) - [ **Gmail to Tavily** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-tavily) Questions ## Openlayer and Tavily, answered ### ### What can start an automation from Openlayer? Any of Openlayer's 2 triggers in the catalog, including New Project and New Test Result. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Tavily when something happens in Openlayer? Any of Tavily's 7 actions, including Create research task, Crawl, Extract and Get research task status. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Tavily to Openlayer? Tavily has no triggers in the catalog today, so automations start in Openlayer. If you need the other direction, ask: your agent reads Tavily's API documentation and adds it. ### ### Do I have to build a connector for Openlayer or Tavily? 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 Openlayer and Tavily 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.