Hive for AI agents

Hive is a project management and team collaboration platform for tracking actions, projects, and workflows. Teams use it to keep project work visible instead of tracking it across separate spreadsheets. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect Hive See the 10 actions ↓

Project managementAPI keyMCP + RESThive.com

AUDIT LOG · HIVEPOLICY: acme-support

09:41:07 · claude · u_8f2read

hive.list_labels

List Labels✓ allowed · 212ms

09:41:08 · claude · u_8f2read

hive.get_action

Get Action✓ allowed · 164ms

09:41:09 · claude · u_8f2write

hive.create_label

Create Label✓ approved · approved by user

09:41:12 · claude · u_8f2destructive

hive.delete_label

Delete Label✕ blocked · policy: deny

EVERY HIVE CALL, ON THE RECORD

01 · USE CASES

What agents do in Hive.

Create a new action item

Create an action in a project from a task mentioned in a status update.

Search for an action

Search actions by keyword to find a task a teammate is asking about.

Delete an action with confirmation

Delete an action only after the assignee confirms it was created by mistake.

02 · ACTIONS

10 Hive actions, graded by risk.

Every Hive action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

Look things up. Allowed by default.

hive.get_action
Get Action
hive.list_labels
List Labels
hive.list_actions
List Actions
hive.list_projects
List Projects
hive.search_actions
Search Actions
hive.list_workspaces
List Workspaces

write

Create and change things. Allow, or ask the user first.

hive.create_label
Create Label
hive.create_action
Create Action

destructive

Delete, cancel or archive. Ask first, or deny outright.

hive.delete_label
Delete Label
hive.delete_action
Delete Action

03 · HOW IT WORKS

Hive in three steps.

01Your users connect HiveThey add their Hive api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, writes like “create Label” can wait for the user, and “delete Label” can be denied outright.
03Any agent can actYour agent calls Hive through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.

POLICY.TS

await arc0.policies.set('hive', {
  read: 'allow',
  write: 'ask',        // create_label
  destructive: 'deny',  // delete_label
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2

04 · AUTH AND DATA

How Hive connects.

Users add their Hive api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Hive connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH: API key
CREDENTIALS: Per-tenant encrypted vault
MODEL SEES: Results only, never credentials
AUDIT LOG: Every call, on every plan

05 · WORKS WITH

Use Hive from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

More project management apps.

Google Tasks18 actions

Moco218 actions

Wrike144 actions

ALL PROJECT MANAGEMENT APPS →

07 · FAQ

Hive and Arc0, answered.

Q01

Can I use Hive with Claude, ChatGPT or Cursor?

Yes. Connect Hive to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Hive actions you allow.

Q02

How do users connect Hive?

Users add their Hive api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Hive actions can my agent take?

10 in total: 6 read, 2 write and 2 destructive, such as “create Label”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Hive?

Yes. Actions like “delete Label” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Hive too?

Yes. The same Hive connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Hive into your agent.

Your users connect Hive once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.

Connect Hive Browse all apps →

Free to build · MCP + REST · Audit log on every plan