--- title: "Connect Swiftype to Parallel Web Systems - APIANT.ai" description: "When \"New Document\" fires in Swiftype, your agent runs \"Add FindAll run\" in Parallel Web Systems." canonical: "https://apiant.ai/connect/swiftype-to-parallel-web-systems" --- # Connect Swiftype to Parallel Web Systems When **New Document** fires in [Swiftype](https://apiant.ai/connections/swiftype), your agent runs **Add FindAll run** in [Parallel Web Systems](https://apiant.ai/connections/parallel-web-systems). Describe the whole flow and it is built, tested on every scenario and kept running. Swiftype **1** trigger Swiftype **14** actions Parallel Web Systems **13** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want Swiftype and Parallel Web Systems 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 Swiftype can start in Parallel Web Systems - When **New Document** in Swiftype then **Add FindAll run** in Parallel Web Systems - When **New Document** in Swiftype then **Add monitor** in Parallel Web Systems 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 Swiftype and Parallel Web Systems ## Triggers and actions 1 trigger · 27 actions - Trigger **New Document** Triggers when a new Document is created. - Action **Add domain** Add a crawler domain to an Engine. - Action **Add engine** Create a new Engine (index). - Action **Create Document** Creates a new Document. - Action **Delete document** Delete a document by document_id from a document type. - Action **Delete domain** Remove a crawler domain from an Engine. - Action **Delete engine** Delete an Engine by id. - Action **Get document** Retrieve a single document by external_id from a document type. - Action **Get engine** Retrieve a single Engine by id or name. - Action **List documents** List documents within a document type/engine. - Action **List domains** List crawler domains configured on an Engine. - Action **List engines** List all Engines for the account. - Action **Recrawl domain** Trigger a recrawl of a domain's crawled content. - Action **Search documents** Perform full-text search over documents within an Engine. - Action **Update document** Update fields on an existing document. - Action **Add FindAll run** Starts a Parallel FindAll run that searches the web for every entity matching your objective and match conditions. The run starts queued; retrieve its status and results with the FindAll run id it returns. - Action **Add monitor** Creates a Parallel monitor that watches a web search query, or the output of an existing task run, for material changes on a schedule. The monitor runs once right away and then on the chosen frequency. - Action **Cancel monitor** Permanently stops a monitor from running. Cancellation cannot be undone; cancelling an already-cancelled monitor changes nothing. - Action **Create Async Web Enrichment** Starts an asynchronous web research/enrichment task run in Parallel. Returns immediately with the run in status 'queued'; fetch the result later with the run id. - Action **Extract web content** Extracts relevant excerpts (and optionally full content) as markdown from up to 20 web URLs. - Action **Fetch Results for Async Runs** Retrieves the result of a Parallel task run (created asynchronously) by its run ID, waiting until the run completes or the timeout elapses. - Action **Find entities by objective** Returns up to the chosen number of people or companies, ranked, that match a natural-language description of the entities you want. - Action **Get FindAll run** Retrieve a FindAll run's status, candidate metrics, generator and metadata. - Action **Get FindAll run result** Retrieve a snapshot of a FindAll run's result: run status and metrics plus every candidate evaluated so far with its match status, output and citations. - Action **Get monitor** Retrieves a monitor by its ID, including its type, status, frequency, query settings, webhook configuration and, for snapshot monitors, the latest output. - Action **List monitors** List monitors in the Parallel account, newest first, optionally filtered by type and status. - Action **Search web** Searches the web with Parallel and returns ranked results with relevant excerpts. - Action **Update monitor** Updates an existing Parallel monitor's frequency, processor, webhook, metadata, query or source settings. Only the fields you fill in are changed. ## Each app on its own - [ **Swiftype** Swiftype is a hosted search solution that lets site owners deliver powerful, customizable search for their...](https://apiant.ai/connections/swiftype) - [ **Parallel Web Systems** Parallel Web Systems is a web search platform that enables AI agents to find, extract, and enrich...](https://apiant.ai/connections/parallel-web-systems) Reviews ## What our customers say ## More from Swiftype - [ **Swiftype to Honeyhive** Observability and evaluation platform for tracing, testing, and monitoring AI agents in production.](https://apiant.ai/connect/swiftype-to-honeyhive) - [ **Swiftype to Trello** Trello is a visual collaboration tool that organizes projects into boards, lists, and cards.](https://apiant.ai/connect/swiftype-to-trello) - [ **Swiftype to JIRA** Atlassian JIRA Cloud — issue tracking and project management.](https://apiant.ai/connect/swiftype-to-jira) - [ **Swiftype to Zoom** Zoom unifies cloud video conferencing, simple online meetings, group messaging, and a software-based...](https://apiant.ai/connect/swiftype-to-zoom) - [ **Swiftype to Twilio** Cloud communications platform for sending SMS/MMS messages, making and managing voice calls, and looking up...](https://apiant.ai/connect/swiftype-to-twilio) - [ **Swiftype to Typeform** Build and publish online forms, surveys, and quizzes with Typeform.](https://apiant.ai/connect/swiftype-to-typeform) ## More into Parallel Web Systems - [ **Salesforce to Parallel Web Systems** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-parallel-web-systems) - [ **monday.com to Parallel Web Systems** monday.com helps you move projects forward fast, letting everyone know what's been done on a task—and what...](https://apiant.ai/connect/monday-com-to-parallel-web-systems) - [ **HubSpot to Parallel Web Systems** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-parallel-web-systems) - [ **Slack to Parallel Web Systems** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-parallel-web-systems) - [ **Google Sheets to Parallel Web Systems** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-parallel-web-systems) - [ **Gmail to Parallel Web Systems** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-parallel-web-systems) Questions ## Swiftype and Parallel Web Systems, answered ### ### What can start an automation from Swiftype? Any of Swiftype's 1 trigger in the catalog, including New Document. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Parallel Web Systems when something happens in Swiftype? Any of Parallel Web Systems's 13 actions, including Create Async Web Enrichment, Update monitor, Add FindAll run and Add monitor. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Parallel Web Systems to Swiftype? Parallel Web Systems has no triggers in the catalog today, so automations start in Swiftype. If you need the other direction, ask: your agent reads Parallel Web Systems's API documentation and adds it. ### ### Do I have to build a connector for Swiftype or Parallel Web Systems? 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 Swiftype and Parallel Web Systems 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.