Integration · Projects & tasks

Connect Claude & ChatGPT to Hivelight

Ask your AI which tasks are due this week, what is happening on a matter, or to apply one of your workflows to a matter in Hivelight. It can list and read matters, tasks, users and workflows, create tasks, move them through their statuses, add notes and archive matters. You get an overview of the workspace without opening every matter.

Connect Hivelight free

Free plan, no credit card. Takes about a minute.

Try asking

“Which tasks are due this week and not done yet?”
The AI lists tasks in that due date range with the status TODO, INPROGRESS or INREVIEW.
“Apply our onboarding workflow to matter 58, starting Monday.”
It finds the workflow and applies it to the matter, which adds the workflow's milestones and tasks from that start date.
“Create a task 'Review draft agreement' on the Smith matter, due Friday, with Sam as reviewer.”
It looks up the matter and Sam's user ID, then creates the task with the due date and reviewer.

What your AI can do

Matters

List, read and update matters, add notes, archive and restore them, and apply workflows to add milestones and tasks.

Tasks

List tasks by matter, milestone, status or due date, create tasks with assignees and reviewers, change status and add notes.

Workspace and team

Read the workspace and its matter types, users and workflow templates, so the AI picks the right IDs.

“Move task 311 to in review.”
It changes the task's status to INREVIEW.
“Add a note to the Smith matter: client called, documents arrive Thursday.”
It adds the note to the matter.
“Archive matter 42, we are done with it.”
It archives the matter. It can be restored later if you need it again.

17 tools for Hivelight

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

add_matter_noteChanges dataAdd a note to a matter by `matter_id`. Put the text or HTML in data.attributes.content.
add_task_noteChanges dataAdd a note to a task by `matter_id` and `task_id`. Put the text or HTML in data.attributes.content.
apply_workflow_to_matterChanges dataApply a workflow to a matter by `matter_id` and `workflow_id`, optionally with a `start_date` (milliseconds since epoch) and a `milestone_id` to start from. This adds the workflow's milestones and tasks to the matter.
archive_matterVisible to othersArchive a matter by `matter_id`. It can be restored later with unarchive_matter.
create_taskChanges dataCreate a task. Put name (required), description, status, dueDate (milliseconds since epoch), assignees and reviewers (user IDs) in data.attributes, and link it with data.relationships.matter.data {type: matter, id} and data.relationships.milestone.data {type: milestone, id}.
get_matterGet one matter by `matter_id`, including its details, milestones and roles.
get_taskGet one task by `task_id`, with its status, dates, assignees and reviewers.
get_userGet one user by `user_id`.
get_workflowGet one workflow by `workflow_id`, including its milestones.
get_workspaceGet the workspace details, including the matter types available in it.
list_mattersList matters in the workspace. Filter by `archived` or `user_ids` and page with `from` and `limit`.
list_tasksList tasks, filtered by `matter_id`, `milestone_id`, `statuses` (comma separated: TODO, INPROGRESS, INREVIEW, DONE) or a due date range (`due_date_from`, `due_date_to`).
list_usersList the users in the workspace. Use their IDs as task assignees or reviewers.
list_workflowsList the workflows (templates of milestones and tasks) available in the workspace. Use a workflow ID with apply_workflow_to_matter.
unarchive_matterDeletesRestore an archived matter by `matter_id` so it becomes active again.
update_matterChanges dataUpdate a matter's name, description or external reference by `matter_id`. Pass the changes in data.attributes (name, description, external-reference).
update_task_statusChanges dataChange a task's status by `task_id`. Set data.attributes.status to TODO, INPROGRESS, INREVIEW or DONE.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose Hivelight from the app list.
2
Paste your key
Paste your Hivelight API address and an API key. The address is https://api.hivelight.com/v1 for US and global accounts, or https://au.api.hivelight.com/v1 for Australian accounts. You need to be an Admin or Owner of the workspace: go to Settings > Integrations > API tab, select the user the key should act as, enter a label and click Create key. Copy the key right away, as it is shown only once.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Hivelight?

It can list and read matters, tasks, users, workflows and the workspace. It can create tasks, change a task's status, add notes to matters and tasks, update a matter's name, description or external reference, apply a workflow to a matter, and archive or restore matters.

Does the AI see my Hivelight credentials?

No. Your Hivelight API key is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start with lookups only. Archiving a matter takes it out of active work, and restoring one makes it active again, so those tools can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT, open Settings › Apps & Connectors › Advanced, turn on Developer mode and add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Hivelight workspace.

Which API address should I use?

Hivelight has two API addresses. Use https://api.hivelight.com/v1 if your account is a US or global account, and https://au.api.hivelight.com/v1 if it is an Australian account. You paste the address together with your API key.