--- title: "Connect Cursor to Infranodus - APIANT.ai" description: "When \"Agent Pull Request Created\" fires in Cursor, your agent runs \"Compare graphs\" in Infranodus." canonical: "https://apiant.ai/connect/cursor-to-infranodus" --- # Connect Cursor to Infranodus When **Agent Pull Request Created** fires in [Cursor](https://apiant.ai/connections/cursor), your agent runs **Compare graphs** in [Infranodus](https://apiant.ai/connections/infranodus). Describe the whole flow and it is built, tested on every scenario and kept running. Cursor **3** triggers Cursor **11** actions Infranodus **8** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want Cursor and Infranodus 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 Cursor can start in Infranodus - When **Agent Pull Request Created** in Cursor then **Compare graphs** in Infranodus - When **New Agent** in Cursor then **Generate advice from graph** in Infranodus 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 Cursor and Infranodus ## Triggers and actions 3 triggers · 19 actions - Trigger **Agent Pull Request Created** Triggers when the selected Cursor cloud agent opens a new GitHub pull request. - Trigger **Agent Status Equals** Triggers when a run on the chosen Cursor agent reaches the status you select, such as Finished or Error. - Trigger **New Agent** Triggered when a new Cursor cloud agent is created. - Action **Add Followup Instruction to Agent** Sends a follow-up instruction to an existing Cursor cloud agent, either starting a new run or steering the run in progress. Returns the new run or how the steer was delivered. - Action **Cancel run** Cancels the active run of a Cursor cloud agent. The run ends in the Cancelled state; start a new run to continue the conversation. - Action **Delete Agent** Permanently deletes a Cursor cloud agent. This cannot be undone. Returns the ID of the deleted agent. - Action **Find Agent Status** Looks up a Cursor cloud agent by its ID and returns its status, name, repositories, latest run and link. - Action **Get run** Returns the status, timestamps, duration, final reply and pushed branches for one run of a Cursor cloud agent. - Action **Launch Agent** Creates a Cursor cloud agent and immediately starts its first run on the task you describe. Returns the new agent and its run. - Action **List agents** Returns the Cursor cloud agents for the connected user, newest first, optionally filtered by pull request URL. - Action **List artifacts** Returns the files a Cursor cloud agent has produced, with each file's path, size and last modified time. Returns at most 100 artifacts. - Action **List models** Returns the recommended Cursor models you can choose from when creating an agent, including their names, aliases, parameters and variants. - Action **List repositories** Returns the GitHub repositories the connected Cursor user can access through Cursor's GitHub App installation. - Action **List runs** Returns the runs of a Cursor cloud agent, newest first, including each run's status, duration, and final reply. - Action **Compare graphs** Builds knowledge graphs from two or more texts and compares them, returning the merged, overlapping (intersection) or differing concepts, topics and gaps. - Action **Find statements** Searches your InfraNodus graphs for statements that contain a word or concept, and returns the matching statements. - Action **Generate advice from graph** Analyzes one of your saved InfraNodus graphs and returns AI-generated advice, such as ideas, questions or responses that bridge the content gaps between its topics. - Action **Generate advice from text** Analyzes a piece of text as a knowledge graph and returns AI-generated advice, ideas or research questions based on the content gaps between its main topics. - Action **Generate graph from Google search results** Builds a knowledge graph of the main topics, clusters and content gaps found in the Google search results for one or more search queries. - Action **Generate graph from search intent** Builds a knowledge graph of the Google searches people make around your queries, showing the main topical clusters and gaps in search intent. - Action **Generate graph from text** Builds a knowledge graph from a text, returning its topical clusters, content gaps, main concepts and network statistics. Optionally saves the graph to your InfraNodus account. - Action **List graphs** Returns the knowledge graphs in your InfraNodus account, optionally filtered by name, graph type, creation date, language or favorite status. ## Each app on its own - [ **Cursor** Cursor is an AI-powered code editor that understands your codebase, supports natural-language coding...](https://apiant.ai/connections/cursor) - [ **Infranodus** Text analysis tool that builds knowledge graphs from documents to surface topics, gaps, and discourse...](https://apiant.ai/connections/infranodus) Reviews ## What our customers say ## More from Cursor - [ **Cursor to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/cursor-to-hubspot) - [ **Cursor to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/cursor-to-salesforce) - [ **Cursor to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/cursor-to-slack) - [ **Cursor to Google Sheets** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/cursor-to-google-sheets) - [ **Cursor to Gmail** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/cursor-to-gmail) - [ **Cursor to Google Calendar** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/cursor-to-google-calendar) ## More into Infranodus - [ **HubSpot to Infranodus** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-infranodus) - [ **Salesforce to Infranodus** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-infranodus) - [ **Slack to Infranodus** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-infranodus) - [ **Google Sheets to Infranodus** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-infranodus) - [ **Gmail to Infranodus** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-infranodus) - [ **Google Calendar to Infranodus** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-infranodus) Questions ## Cursor and Infranodus, answered ### ### What can start an automation from Cursor? Any of Cursor's 3 triggers in the catalog, including Agent Pull Request Created, New Agent and Agent Status Equals. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Infranodus when something happens in Cursor? Any of Infranodus's 8 actions, including Compare graphs, Find statements, Generate advice from graph and Generate advice from text. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Infranodus to Cursor? Infranodus has no triggers in the catalog today, so automations start in Cursor. If you need the other direction, ask: your agent reads Infranodus's API documentation and adds it. ### ### Do I have to build a connector for Cursor or Infranodus? 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 Cursor and Infranodus 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.