# Hive L4 · Runs on its own

Hive is a project management tool.

**Can an AI agent use Hive? Yes, in a browser.** Our agent got into Hive on its own in 9 minutes and did all 8 of its core tasks.

Category: Project management · Connects by: MCP, API · Agent payments: None found · Driven: 27 Oct 2026

**How to connect**
- MCP server URL: `https://developers.hive.com/mcp` (streamable HTTP, tested in our drive). Source: https://developers.hive.com/mcp

**Level 4: Runs on its own.** An agent does the core work and can stop paying on its own.
- Got in by: Email and password (9 minutes, in a browser)
- Got as far as: Pay: reaches the checkout (Stopped at the $7 a month charge)
- To reach L5: Pay without a person.

1 drive, awaiting confirmation

[What the levels mean](https://agentdrives.com/method/levels?via=md)

## From finding it to leaving

What an agent managed without a person, at each step.

1. **Find**: On its own. Docs it can act on: llms.txt, an OpenAPI and an MCP server. (308 doc pages read)
2. **Get in**: On its own. Sign-up in a browser. (9 minutes)
3. **Use**: On its own. Did: create, update, assign, date, complete and delete tasks through the API; create, rename, copy and delete projects through the API. (8 of 8 core tasks)
4. **Pay**: Reaches the checkout. Stopped at the $7 a month charge.
5. **Leave**: On its own. Nothing to cancel, deletes its account.

## Getting in

One way in, and it worked without a person.

The way that worked: **Email and password**, 9 minutes. Needs an inbox and a browser. No person needed.

- Agent on a server (API, MCP, CLI): No. Stops at sign-up: it works only in a browser.
- Assistant in its own browser (Like ChatGPT agent): Partly. Signs up, confirms its email and does all of the core work. Payment: reaches the checkout, stopped at the $7 a month charge.
- Signed agent (Known to Cloudflare): Yes. The sign-up page opens.

## What an agent can do with Hive

All 8 core tasks done, and 15 of 22 others. One task not tried isn't counted.

- Reliability: core tasks that worked on all 3 runs: 91 of 100
- Handles mistakes: clear errors, retries without duplicates, honest limits: 45 of 100
- Surface tested: documented routes, tools and commands run and checked: 37 of 100
- Docs accuracy: documented operations that behaved as the docs say: 90 of 100
- Docs completeness: how fully the docs describe each operation: 51 of 100

Core tasks:

| Task | Result | Done through |
|---|---|---|
| Create a task or issue | Done | API |
| Update a task | Done | API |
| Complete a task or change its status | Done | API |
| Create a project or board | Done | API |
| Assign a task | Done | API |
| Set a task's due date | Done | API |
| Create a board, Gantt or calendar view | Done | Web app |
| Build an automation workflow | Done | API |

15 of 22 other tasks done:

- Comment on a task: Done
- Add subtasks or a checklist: Done
- Attach a file to a task: Done
- Add a label to a task: Done
- Set a custom field on a task: Done
- Search or filter tasks: Done
- Bulk-edit tasks: Done
- Log time on a task or project: Done
- Build a dashboard of work data: Done
- Start from a template: Done
- Ask the built-in AI assistant a question: Done
- Delegate a task to the built-in AI agent: Done
- Generate or rewrite content with AI: Done
- Invite a member: Done
- Set a member's role or permissions: Done
- Create a form: Partly
- Read form responses: Partly
- Plan a sprint: Partly
- Register a webhook: Partly
- Proof a file with annotations: Partly
- Connect a third-party integration: Partly
- Request an approval on a task or file: Paid plan
- Track CRM deals and accounts: Paid plan
- Run finance workflows (estimates, billing, invoicing): Paid plan
- Provision users with SCIM: Paid plan
- Configure SAML SSO: Paid plan
- Capture a task from email or chat: Not tried

The plans they need:

- Proof a file with annotations: Proofing & Approvals add-on
- Run finance workflows: Finance add-on

Paid-plan tasks don't count toward the level. The drive used the no-card trial.

What it can't do, and why:

- Get or replace an API key without a browser: Keys are shown and regenerated only in the web settings.
- Register a webhook from the current API reference: The allowed trigger values are only in the old reference.
- Create a sprint, view, automation or form through an API: These exist only in the web app.
- Pay without a card: The only checkout is a card form; there is no machine payment.
- Delete the account without a browser: Deletion is a button in profile settings only.

**Surface audit:** 362 documented operations, 148 run, 128 passed, 15 not as documented, 57 blocked (sandbox or plan limits), 140 not run for time, 18 left out to stay safe.

## How an agent connects

MCP, API and llms.txt found.

Agent surfaces: API tested · MCP tested · CLI none found · SDK none found · Docs tested · Agent payments none found. Issues found: 24.

- **MCP server**: All tested. Official server. Docs server (ReadMe), 6 tools, 28 Jul 2026. https://developers.hive.com/mcp (6 tools across its docs) 6 tools listed without signing in on 31 Oct 2026: `list-endpoints`, `get-endpoint`, `search-endpoints`, `list-specs`, `execute-request`, `get-server-variables`.
- **API**: 140 tested. REST v2, 92 operations plus 12 SCIM; GraphQL API documented separately. (351 operations across its docs)
- **OpenAPI**: Unknown.
- **CLI**: None found.
- **SDK**: None found.
- **llms.txt**: Yes. https://hive.com/llms.txt
- **Agent payments**: None found. The checkout: Reached the card form and stopped: Starter, $7 a month; Checkout: Chargebee; An invisible bot check loaded at checkout.
- **Docs**: Some gaps. Covers getting started, auth, error codes and code examples. 5 of 7 documented ways to do the core work worked when tried. (308 of 315 pages read)

[The standards](https://agentdrives.com/standard)

## Tips for agent builders

- Sign up at app.hive.com/join with a work email; the 6-digit code arrives in seconds. Copy the API key, User ID and Workspace ID from avatar > My profile > API info (URL ?userSettings=apiInfo).
- Send the key as the api_key header to https://app.hive.com/api/v2; v1 /testcredentials?user_id= checks it.
- Due date is the deadline field (stored at 12:00 UTC); status values are the project's statuses (Unstarted, In progress, Completed); subtasks: create, then PUT {"parent": id}.
- Bulk updates take {"actions": [{"_id": ..., ...}]}, not a bare array.
- Time entries, dashboards, forms and webhooks are in the GraphQL API at https://prod-gql.hive.com/graphql with the same api_key header; the getting-started example query getUser does not exist, use user.
- Search with GET /workspaces/{id}/actions/search?searchTerm=...; filters[projectId] on the list endpoint is ignored.
- A calendar-connect modal covers the web app on every load: click "I don't want any calendar features" first.
- Webhook triggers are actions::i, actions::u, projects::i and projects::u (developers.hive.com/v1.0/reference/object-13); the current reference does not list them.

## How Hive compares

In Project management: 1st of 5 Project management products our agent got into on its own.

- [Nifty](https://agentdrives.com/tools/niftypm.md?via=md): L4, Gets in on its own
- **Hive** (this page): L4, Gets in on its own
- [Plane](https://agentdrives.com/tools/plane.md?via=md): L4, Gets in on its own
- [monday.com](https://agentdrives.com/tools/monday.md?via=md): L4, Gets in on its own
- [Shortcut](https://agentdrives.com/tools/shortcut.md?via=md): L4, Gets in on its own
- [Asana](https://agentdrives.com/tools/asana.md?via=md): L1, Can't sign up on its own
- [Basecamp](https://agentdrives.com/tools/basecamp.md?via=md): L1, Can't sign up on its own
- [ClickUp](https://agentdrives.com/tools/clickup.md?via=md): L1, Can't sign up on its own

[All 15 in Project management](https://agentdrives.com/categories/project-management?via=md)

Sorted by level, then work done, then time to the first call. [How we rank](https://agentdrives.com/method?via=md#order)

On our standard (24 criteria: against other project management products where we measured 5 or more, otherwise against every product we measured):

- [Every way in works for an agent](https://agentdrives.com/standard#in-11): **Ahead of most** 10 of 13 others (project management products) lower, 3 the same.
- [Export before leaving](https://agentdrives.com/standard#leave-03): **Ahead of most** 10 of 14 others (project management products) lower, 4 the same.
- [A request id on every answer](https://agentdrives.com/standard#err-07): **Ahead of most** 4 of 7 others (project management products) lower, 3 the same.
- [The best way in is built for agents](https://agentdrives.com/standard#in-12): **Ahead of most** 8 of 13 others (project management products) lower, 4 the same, 1 higher.
- [Results sized for a context window](https://agentdrives.com/standard#mcp-09): **Ahead of most** 16 of 31 others (every product) lower, 15 the same.
- [A tool list that fits](https://agentdrives.com/standard#mcp-11): **Ahead of most** 33 of 65 others (every product) lower, 32 the same.
- [Pages fit one fetch](https://agentdrives.com/standard#docs-08): **Level with most** 7 of 13 others (project management products) the same, 6 lower.
- [Prices an agent can read](https://agentdrives.com/standard#find-06): **Level with most** 5 of 8 others (project management products) the same, 3 lower.
- [Limits known before they hit](https://agentdrives.com/standard#lim-02): **Ahead of most** 27 of 47 others (every product) lower, 5 the same, 15 higher.
- [Fast to the first call](https://agentdrives.com/standard#in-03): **Level with most** 3 of 4 others (project management products) the same, 1 lower.
- [Errors say what to do next](https://agentdrives.com/standard#err-03): **In the middle** 2 of 5 others (project management products) lower, 2 the same, 1 higher.
- [Answers sized for an agent](https://agentdrives.com/standard#api-04): **Level with most** 5 of 6 others (project management products) the same, 1 lower.
- [Structured results](https://agentdrives.com/standard#mcp-08): **In the middle** 15 of 36 others (every product) lower, 10 the same, 11 higher.
- [Tool names that sort themselves](https://agentdrives.com/standard#mcp-03): **Level with most** 61 of 65 others (every product) the same, 4 lower.
- [Real status codes](https://agentdrives.com/standard#err-01): **The same as all** 11 others (project management products).
- [WebMCP tools on the web app](https://agentdrives.com/standard#proto-02): **The same as all** 4 others (project management products).
- [Typed, tight input schemas](https://agentdrives.com/standard#mcp-06): **Level with most** 39 of 65 others (every product) the same, 10 lower, 16 higher.
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05): **Level with most** 8 of 9 others (project management products) the same, 1 higher.
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11): **Level with most** 10 of 13 others (project management products) the same, 3 higher.
- [Truthful annotations](https://agentdrives.com/standard#mcp-07): **Behind most** 34 of 65 others (every product) higher, 13 the same, 18 lower.
- [Agents pick the right tool](https://agentdrives.com/standard#mcp-05): **Level with most** 44 of 65 others (every product) the same, 1 lower, 20 higher.
- [Errors a program can read](https://agentdrives.com/standard#err-02): **Behind most** 3 of 5 others (project management products) higher, 2 the same.
- [Descriptions that say when to use the tool](https://agentdrives.com/standard#mcp-04): **Behind most** 46 of 65 others (every product) higher, 19 the same.
- [A path written for agents](https://agentdrives.com/standard#docs-10): **Behind most** 11 of 13 others (project management products) higher, 2 the same.

[How each criterion is graded](https://agentdrives.com/standard)

## For the team behind Hive

**7 things to fix for agents.**

Agent blockers: 3 found · Agent surfaces: 21 issues found. Safety review: no issues found.

Our agent got through Pay only in part. Prove Hive is yours, then see where each issue is, read your safety findings and ask for a free drive after a fix. How to fix each one comes with the Audit.

- Find: Clear
- Get in: Clear
- Use: Clear
- Pay: Partly
- Leave: Clear

[Claim Hive, free](https://agentdrives.com/app/products?add=hive.com&ref=listing) · [What a drive covers](https://agentdrives.com/method?via=md)

## Where Hive fits

- Category: [Work and collaboration](https://agentdrives.com/categories/work?via=md), [Project management](https://agentdrives.com/categories/project-management?via=md)
- Tasks: [Invite a member](https://agentdrives.com/tasks/invite-a-member), [Set a member's role or permissions](https://agentdrives.com/tasks/set-a-member-s-role-or-permissions), [Create a task or issue](https://agentdrives.com/tasks/create-a-task-or-issue), [Start from a template](https://agentdrives.com/tasks/start-from-a-template), [Comment on a task](https://agentdrives.com/tasks/comment-on-a-task), [Attach a file to a task](https://agentdrives.com/tasks/attach-a-file-to-a-task)
- Standards: [MCP](https://agentdrives.com/standards/mcp) (tools an agent can call), [llms.txt](https://agentdrives.com/standards/llms-txt) (its docs, listed for agents)
- Steps: [Find](https://agentdrives.com/access/find), [Get in](https://agentdrives.com/access/get-in), [Use](https://agentdrives.com/access/use), [Pay](https://agentdrives.com/access/pay), [Leave](https://agentdrives.com/access/leave)
- Rivals: [monday.com](https://agentdrives.com/tools/monday?via=md) (L4), [Nifty](https://agentdrives.com/tools/niftypm?via=md) (L4), [Plane](https://agentdrives.com/tools/plane?via=md) (L4)

Data: [JSON](https://agentdrives.com/api/tools/hive.json?via=md) · [Markdown](https://agentdrives.com/tools/hive.md?via=md) · [History](https://agentdrives.com/tools/hive/history?via=md) · [Atom](https://agentdrives.com/feeds/tools/hive.atom) · [JSON Feed](https://agentdrives.com/feeds/tools/hive.json) · licence [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)

**Found an error?** [Tell us on this page](https://agentdrives.com/tools/hive?via=md#correct) or read [how corrections work](https://agentdrives.com/corrections?via=md).