---
title: "Connect Ninety to Lakera AI Guardrails - APIANT.ai"
description: "When \"New Issue Created\" fires in Ninety, your agent runs \"Check for Jailbreak Attempt\" in Lakera AI Guardrails."
canonical: "https://apiant.ai/connect/ninety-to-lakera-ai-guardrails"
---

# Connect Ninety to Lakera AI Guardrails

When **New Issue Created** fires in [Ninety](https://apiant.ai/connections/ninety), your agent runs **Check for Jailbreak Attempt** in [Lakera AI Guardrails](https://apiant.ai/connections/lakera-ai-guardrails). Describe the whole flow and it is built, tested on every scenario and kept running.

Ninety **4** triggers Ninety **21** actions Lakera AI Guardrails **5** actions

What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.

## What do you want Ninety and Lakera AI Guardrails 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 Ninety can start in Lakera AI Guardrails

- When **New Issue Created** in Ninety then **Check for Jailbreak Attempt** in Lakera AI Guardrails
- When **New Measurable** in Ninety then **Check for Prompt Injection** 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 Ninety and Lakera AI Guardrails

## Triggers and actions 4 triggers · 26 actions

- Trigger

**New Issue Created**

Triggered when a new issue is created in Ninety, optionally only on one team or only short-term vs long-term issues.

- Trigger

**New Measurable**

Triggered when a new measurable (KPI) is added to your Ninety scorecard, optionally only those tracked over a given period like weekly or monthly.

- Trigger

**New Team**

Triggered when a new team is created in your Ninety company.

- Trigger

**To-Do Created, Updated, or Deleted**

Triggered when a to-do is created or changed in Ninety — including being completed or archived — optionally only on one team or only personal to-dos. Ninety's API does not report hard deletions, so a removed to-do simply stops appearing rather than firing this trigger.

- Action

**Create Issue**

Creates an issue on a Ninety team's issues list.

- Action

**Create Milestone**

Creates a milestone on a Ninety rock, with a title and due date.

- Action

**Create Rock**

Creates a rock (a quarterly goal) for a Ninety team, with a due date, status and level.

- Action

**Create To-Do**

Creates a to-do on a Ninety team, with a due date and optional description.

- Action

**Delete Issue**

Deletes an existing Issue in Ninety by its ID.

- Action

**Delete Measurable Note**

Deletes the note on a Measurable for one scorecard period.

- Action

**Delete Measurable Score**

Deletes the score on a Measurable for one scorecard period.

- Action

**Delete Rock**

Deletes a Rock in Ninety by its ID. Returns the deleted Rock's ID along with the status Ninety returned.

- Action

**Delete To-Do**

Deletes a to-do in Ninety by its ID. Use it to remove a to-do that was created by mistake or is no longer needed.

- Action

**Find Issue**

Searches Ninety for issues matching the words you provide, optionally narrowed to one team or to short-term vs long-term issues. Returns the matching issues.

- Action

**Find Measurable**

Searches Ninety's scorecard for measurables (KPIs) matching the words you provide, optionally limited to a tracking period like weekly or monthly. Returns the matching measurables.

- Action

**Find Milestone**

Searches Ninety for milestones by title. Ninety carries milestones on their rocks, so this reads the rocks (optionally just one team's) and returns the milestones whose title matches, optionally limited to a single rock.

- Action

**Find Rock**

Searches Ninety for rocks (quarterly goals) matching the words you provide, optionally narrowed to one team or one status. Returns the matching rocks.

- Action

**Find Team**

Returns the teams in your Ninety company, optionally only those whose name contains the words you provide. Use it to get the team ID other Ninety actions need.

- Action

**Find To-Do**

Searches Ninety for to-dos matching the words you provide, optionally narrowed to one team, to personal to-dos, or to finished vs open ones. Returns the matching to-dos.

- Action

**Update Issue**

Changes an existing issue in Ninety — its title, detail, team, priority, short-term/long-term setting, or whether it is solved. Fields you leave blank are left as they are.

- Action

**Update Measurable Note**

Saves the note on a Ninety scorecard measurable for one period, replacing any note already there.

- Action

**Update Measurable Score**

Records the score on a Ninety scorecard measurable for one period, replacing any score already there.

- Action

**Update Milestone**

Changes an existing milestone in Ninety — its title, detail, due date, owner, or whether it is finished. Fields you leave blank are left as they are.

- Action

**Update Rock**

Changes an existing rock (quarterly goal) in Ninety — its title, detail, status, owner, team, quarter, due date, or whether it is archived. Fields you leave blank are left as they are.

- Action

**Update To-Do**

Changes an existing to-do in Ninety — its title, detail, due date, owner, team, repeat setting, or whether it is done or archived. Fields you leave blank are left as they are.

- Action

**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.

- Action

**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.

- Action

**Detect PII**

Screens text with AI Guardrails and returns any personal information (PII) found, with its type and location in the text.

- Action

**Detect Toxicity**

Screens text for toxic, hateful, violent, sexual or profane content using your AI Guardrails project policy and returns whether it was flagged.

- Action

**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.

## Each app on its own

- [ **Ninety** Ninety is a platform that helps organizations execute their strategies by aligning goals, managing tasks...](https://apiant.ai/connections/ninety)
- [ **Lakera AI Guardrails** Lakera AI Guardrails is a security platform detecting prompt injections, jailbreaks, PII, toxicity, and...](https://apiant.ai/connections/lakera-ai-guardrails)

Reviews

## What our customers say

## More from Ninety

- [ **Ninety to Steady** Steady is a subscription platform for blogs, journalism, podcasts and other content creators.](https://apiant.ai/connect/ninety-to-steady)
- [ **Ninety to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/ninety-to-salesforce)
- [ **Ninety to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/ninety-to-slack)
- [ **Ninety to Stripe** Stripe is a payment processing platform for online businesses.](https://apiant.ai/connect/ninety-to-stripe)
- [ **Ninety to Shopify** Shopify is a commerce platform for online stores and retail point-of-sale.](https://apiant.ai/connect/ninety-to-shopify)
- [ **Ninety to QuickBooks Online** QuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...](https://apiant.ai/connect/ninety-to-quickbooks-online)

## More into Lakera AI Guardrails

- [ **HubSpot to Lakera AI Guardrails** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-lakera-ai-guardrails)
- [ **Salesforce to Lakera AI Guardrails** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-lakera-ai-guardrails)
- [ **Slack to Lakera AI Guardrails** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-lakera-ai-guardrails)
- [ **Google Sheets to Lakera AI Guardrails** Google Sheets](https://apiant.ai/connect/google-sheets-to-lakera-ai-guardrails)
- [ **Gmail to Lakera AI Guardrails** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-lakera-ai-guardrails)
- [ **Google Calendar to Lakera AI Guardrails** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-lakera-ai-guardrails)

Questions

## Ninety and Lakera AI Guardrails, answered

###

### What can start an automation from Ninety?

Any of Ninety's 4 triggers in the catalog, including New Issue Created, New Measurable, New Team and To-Do Created, Updated, or Deleted. 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 Ninety?

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 Ninety?

Lakera AI Guardrails has no triggers in the catalog today, so automations start in Ninety. 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 Ninety 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 Ninety 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.
