Integration
Connect Cursion to Lakera AI Guardrails
When New Flow fires in Cursion, your agent runs Check for Jailbreak Attempt in Lakera AI Guardrails. Describe the whole flow and it is built, tested on every scenario and kept running.
What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.
Build solutions, not workarounds.
What do you want Cursion and Lakera AI Guardrails to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne 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.aiStart Claude Code there, approve the server, and sign in in the browser page it opens.
Claude Code guide (opens in a new tab)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)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)Zed
Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.
Setup guide (opens in a new tab)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)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)Example flows
What Cursion can start in Lakera AI Guardrails
When New Flow in Cursion
then Check for Jailbreak Attempt in Lakera AI Guardrails
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 Cursion and Lakera AI Guardrails
Triggers and actions 5 triggers · 22 actions
- New Flow
Triggers when a new Flow is created in your Cursion account.
- New Page
Triggers when a new page is added to a Cursion site.
- New Scan
Triggers when a new Scan is created for the selected Cursion page.
- New Site
Triggers when a new site is added to your Cursion account.
- New Test
Triggers when a new Test (a comparison of two scans) is created for a page.
- Add case
Generates a new test case for a site from a plain-language prompt and returns the process tracking its creation.
- Add flow
Creates a Flow in Cursion — a named sequence of steps (scans, cases, alerts) that FlowRuns execute.
- Create CaseRun
Runs a saved Case against a Site, creating a CaseRun that executes in the background and returns immediately.
- Create FlowRun
Runs a Flow against a Site and returns the new FlowRun, which completes asynchronously.
- Create Page
Creates a Page under a Cursion Site and, unless skipped, starts its initial baseline Scan.
- Create Scan
Starts a new Scan of a Site's pages in Cursion. The scan runs in the background and may take several minutes to complete.
- Create Site
Creates a Site in Cursion for a domain, then crawls it for pages and runs initial baseline scans in the background.
- Delete site
Deletes a site and, with it, all of the site's scans, tests, schedules and alerts.
- Get FlowRun
Returns a single FlowRun — the result of running a Flow against a Site — including its nodes, status and logs.
- Get scan
Returns a single Cursion scan with its HTML, logs, Lighthouse and security scores, and screenshots.
- Get site
Returns a single Cursion site with its URL, tags, crawl times and latest scan and test summary.
- Get test
Returns a single Test, the comparison of two scans of a page, with its scores, status and deltas.
- List flows
Returns the flows in your Cursion account, including each flow's steps (nodes) and connections (edges).
- List pages
Returns the pages that belong to a Cursion site, with each page's URL, tags and latest scan and test results.
- List scans
Returns the scans captured for a Cursion page, ordered by creation time.
- List sites
Returns the sites in your Cursion account, newest first, with each site's URL, tags and latest scan and test details.
- List tests
Returns the Tests run against a Cursion Page, ordered by creation time.
- Check for Jailbreak Attempt
Screens a piece of text with Lakera AI Guardrails and returns whether it was flagged as a jailbreak or prompt attack, with the per-detector breakdown.
- Check for Prompt Injection
Screens a piece of text with Lakera AI Guardrails and returns whether it was flagged, with a per-detector breakdown so prompt injection detections can be checked.
- Detect PII
Screens text with AI Guardrails and returns any personal information (PII) found, with its type and location in the text.
- Detect Toxicity
Screens text for toxic, hateful, violent, sexual or profane content using your AI Guardrails project policy and returns whether it was flagged.
- Screen Content
Screens an LLM conversation (and optionally tool definitions) against your AI Guardrails project policy and returns whether it was flagged, with optional per-detector breakdown and match locations.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from Cursion
Cursion to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Cursion to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Cursion to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Cursion to Google SheetsGoogle Sheets
Cursion to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Cursion to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
More into Lakera AI Guardrails
Questions
Cursion and Lakera AI Guardrails, answered
What can start an automation from Cursion?
Any of Cursion's 5 triggers in the catalog, including New Flow, New Page, New Scan and New Site. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Lakera AI Guardrails when something happens in Cursion?
Any of Lakera AI Guardrails's 5 actions, including Check for Jailbreak Attempt, Check for Prompt Injection, Detect PII and Detect Toxicity. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Lakera AI Guardrails to Cursion?
Lakera AI Guardrails has no triggers in the catalog today, so automations start in Cursion. If you need the other direction, ask: your agent reads Lakera AI Guardrails's API documentation and adds it.
Do I have to build a connector for Cursion or Lakera AI Guardrails?
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 Cursion and Lakera AI Guardrails 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.