Integration
Connect Roll to Spike.sh
When New Company fires in Roll, your agent runs Add alert rule in Spike.sh. 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 Roll and Spike.sh 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 Roll can start in Spike.sh
When New Company in Roll
then Add alert rule in Spike.sh
When New Project in Roll
then Add escalation in Spike.sh
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 Roll and Spike.sh
Triggers and actions 3 triggers · 36 actions
Trigger
New CompanyTriggers when a new company is created.
Trigger
New ProjectTriggers when a new project is created.
Trigger
New Time RecordTriggers when a new time record is created.
Action
Add taskCreate a task via the Roll GraphQL API task add mutation.
Action
Create CompanyCreates a new company.
Action
Create ProjectCreates a new project.
Action
Create Time RecordCreates a new time record.
Action
Find CompanyFinds an existing company.
Action
Find employeeSearch employees via the Roll GraphQL API employees query.
Action
Find ProjectFinds an existing project.
Action
Find Time RecordLooks up Roll time records via the GraphQL time query.
Action
Update projectUpdate a project via the Roll GraphQL API project update mutation.
Action
Update taskUpdate a task via the Roll GraphQL API task update mutation.
Action
Update time recordUpdate a time entry via the Roll GraphQL API time update mutation.
Action
Acknowledge incidentAcknowledge one or more Spike.sh incidents by counter id or incident id.
Action
Add alert ruleCreate a new alert routing/automation rule with conditions and actions.
Action
Add escalationCreates a new escalation policy for a Spike.sh team, defining who is notified, through which channel, and how long to wait between steps.
Action
Add integrationCreate a new integration for a team (source system that sends alerts into Spike).
Action
Add on-callCreate a new on-call schedule for a team.
Action
Add serviceCreate a new service in a team, with name and description.
Action
Create IncidentCreates a Spike incident through one of your integrations and sends alerts. The integration decides which service and escalation policy the incident is routed to.
Action
Delete alert ruleArchives (soft-deletes) a Spike alert rule so it no longer applies to incoming incidents.
Action
Delete escalationArchives (soft-deletes) a Spike escalation policy by its ID.
Action
Escalate incidentEscalates one or more Spike incidents to the next step of their escalation policy.
Action
Get escalationGet escalation policy details by id.
Action
Get incidentFetch a single incident by counter id.
Action
Get integrationFetches an integration by its token, including its name, type, service, escalation settings and webhook URL. An error occurs if the integration is not found.
Action
Get serviceGet a Spike service's details, along with its incidents and open-incident count.
Action
List alert rulesLists all alert rules (enabled and disabled) configured for a Spike team.
Action
List escalationsLists the escalation policies that belong to a Spike team.
Action
List incidentsLists the incidents for a Spike.sh team.
Action
List on-callsLists the on-call schedules for a team.
Action
List servicesLists the services in a Spike team.
Action
List teamsLists every team in your Spike organisation. Use a team's ID from here wherever other Spike actions ask for a team.
Action
Resolve incidentResolve one or more incidents by counter id array.
Action
Update alert ruleReplace an existing Spike alert rule's name, conditions and actions.
Action
Update escalationReplaces an existing escalation policy's name, steps and start delay. The whole policy is replaced, so send every step you want to keep.
Action
Update on-callUpdates an on-call schedule's name and/or moves it to another team. Rotations and layers are not changed by this action.
Action
Update serviceUpdates the name and/or description of an existing Spike.sh service.
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 Roll
Roll to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Roll to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Roll to StripeStripe is a payment processing platform for online businesses.
Roll to ShopifyShopify is a commerce platform for online stores and retail point-of-sale.
Roll to TrelloTrello is a visual collaboration tool that organizes projects into boards, lists, and cards.
Roll to ZoomZoom unifies cloud video conferencing, simple online meetings, group messaging, and a software-based...
More into Spike.sh
HubSpot to Spike.shHubSpot is your all-in-one stop for all of your marketing software needs.
Salesforce to Spike.shSalesforce is a leading enterprise customer relationship management (CRM) platform.
Slack to Spike.shSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Google Sheets to Spike.shGoogle Sheets
Gmail to Spike.shGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to Spike.shGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Questions
Roll and Spike.sh, answered
What can start an automation from Roll?
Any of Roll's 3 triggers in the catalog, including New Company, New Project and New Time Record. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Spike.sh when something happens in Roll?
Any of Spike.sh's 25 actions, including Create Incident, Update alert rule, Update escalation and Update on-call. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Spike.sh to Roll?
Spike.sh has no triggers in the catalog today, so automations start in Roll. If you need the other direction, ask: your agent reads Spike.sh's API documentation and adds it.
Do I have to build a connector for Roll or Spike.sh?
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 Roll and Spike.sh 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.