Integration
Connect Float to Parallel Web Systems
When something happens in Float, your agent does the next thing in Parallel Web Systems. Describe it 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 Float and Parallel Web Systems to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiAny 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 Float can start in Parallel Web Systems
When New Allocation in Float
then Add FindAll run 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 Float and Parallel Web Systems
Triggers and actions 15 triggers · 34 actions
- New Allocation
Triggers when a new allocation is created.
- New Client
Triggers when a new client is added.
- New Department
Triggers when a new department is added.
- New Logged Time
Triggers when a new logged time is created.
- New Milestone
Triggers when a new milestone is created.
- New Person
Triggers when a new person is added.
- New Phase
Triggers when a new phase is created.
- New Project
Triggers when a new project is created.
- New Project Task
Triggers when a new project task is created.
- New Time Off
Triggers when a new time off is created.
- Updated Allocation
Triggers when an allocation is modified.
- Updated Logged Time
Triggers when a logged time is modified.
- Updated Phase
Triggers when a phase is modified.
- Updated Project
Triggers when a project is modified.
- Updated Project Task
Triggers when a project task is modified.
- Create Allocation
Creates a new allocation.
- Create Client
Creates a new client.
- Create Department
Creates a new department.
- Create Logged Time
Creates a new logged time.
- Create Milestone
Creates a new milestone.
- Create Person
Creates a new person.
- Create Phase
Creates a new phase.
- Create Project
Creates a new project.
- Create Project Task
Creates a new project task.
- Create Time Off
Creates a new time off.
- Find Allocation
Finds an allocation by ID.
- Find Logged Time
Finds a logged time by ID.
- Find Person
Finds a person by ID, email, or tag(s).
- Find Project
Finds a project by ID, project_code, or tag(s).
- Update Allocation
Update an existing allocation by ID.
- Update Logged Time
Update an existing logged time entry by ID.
- Update Milestone
Update an existing milestone by ID.
- Update Person
Update an existing person by ID.
- Update Phase
Update an existing phase by ID.
- Update Project
Update an existing project by ID.
- Update Project Task
Update an existing project task by ID.
- 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.
- 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.
- Cancel monitor
Permanently stops a monitor from running. Cancellation cannot be undone; cancelling an already-cancelled monitor changes nothing.
- 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.
- Extract web content
Extracts relevant excerpts (and optionally full content) as markdown from up to 20 web URLs.
- 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.
- 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.
- Get FindAll run
Retrieve a FindAll run's status, candidate metrics, generator and metadata.
- 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.
- Get monitor
Retrieves a monitor by its ID, including its type, status, frequency, query settings, webhook configuration and, for snapshot monitors, the latest output.
- List monitors
List monitors in the Parallel account, newest first, optionally filtered by type and status.
- Search web
Searches the web with Parallel and returns ranked results with relevant excerpts.
- Update monitor
Updates an existing Parallel monitor's frequency, processor, webhook, metadata, query or source settings. Only the fields you fill in are changed.
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 Float
Float to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Float to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Float to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Float to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Float to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Float to Google DriveGoogle Drive is a cloud storage solution for uploading, sharing, and collaborating on files across devices...
More into Parallel Web Systems
Google Sheets to Parallel Web SystemsGoogle Sheets
Questions
Float and Parallel Web Systems, answered
What can start an automation from Float?
Any of Float's 15 triggers in the catalog, including New Allocation, New Client, New Department and New Logged Time. 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 Float?
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 Float?
Parallel Web Systems has no triggers in the catalog today, so automations start in Float. 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 Float 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.
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.