ClickUp

# Fix list: ClickUp

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/clickup, the October 2026 research run, assessed 8 October 2026. Grade C, 60.9 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on ClickUp: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Plan prices are public, Free Forever, Unlimited at $7 a seat a month billed yearly or $10 monthly, Business at $12 or $19, Enterprise through sales. API and MCP calls are not priced per call, and the MCP daily caps lift with the Everything AI add-on at $28 a seat a month (10). Free Forever includes the API and the MCP server at 100 MCP calls per rolling 24 hours. We did not go through signup to confirm no card is asked for (20). Dynamic client registration lets an MCP client register itself, but a person signs in and authorises the Workspace in a browser (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 2. Agent ergonomics, 48 out of 100, up to 8.5 more on the total

Why it scored 48: 48 documented MCP tools (5). The OAuth metadata advertises separate read and write scopes and `clickup_get_task` takes an `include` list, per ClickUp's plugin skills (3 more, 8 of 25). Get Tasks filters by status, assignee, tag, dates and Custom Fields at 100 tasks a page, v3 uses `limit` and `next_cursor`, and MCP has a Workspace search tool. No field selection on v2 (16 of 20). Errors carry `err` and an `ECODE`, and v3 adds `status`, `message` and `trace_id`. Only the OAuth codes are explained (12 of 20). No idempotency keys in either spec. `readOnlyHint` and `destructiveHint` could not be checked without an OAuth session. MCP rate errors return `retryAfter` (5 of 20). Create Task needs only `name`. No official SDK found on npm or in the ClickUp GitHub organisation. The official plugin adds three skills that preview a plan before writing (7 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 3. Security & auth, 64 out of 100, up to 6.3 more on the total

Why it scored 64: The MCP server takes only OAuth 2.1 with PKCE (S256), dynamic client registration and resource indicators, with two scopes, read and write. The REST API takes a personal token (`pk_`) or an OAuth 2.0 token, neither of which expires or carries scopes (24 of 30). The read scope, the user's choice of Workspaces at authorisation and ClickUp's permission model limit reach. The MCP FAQ says deletion tools are withheld as a safety measure, while the tools page lists Delete task. No server-side confirmation step is documented (12 of 20). Tools return task, comment, Doc and Chat text written by other people, and no injection guidance was found (3 of 15). Audit Log is an Enterprise feature with a v3 endpoint, and MCP responses carry `X-Correlation-ID`. Whether MCP calls are logged per tool was not established (8 of 15). security.txt valid until 1 September 2027, a disclosure policy with safe harbour, SOC 1 and SOC 2 Type 2, ISO 27001, 27017, 27018, 27701 and 42001 stated, third-party penetration tests. No paid bounty found (17 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 4. Reliability, 74 out of 100, up to 5.2 more on the total

Why it scored 74: Graded on the hosted MCP server and the public REST API, with the hosted lines. Status page at status.clickup.com on incident.io with 22 components, Public API among them (20). The incident feed shows one incident since 20 July 2026, degraded Search for some US users on 27 July for about 2 h 35 min, marked minor, and two completed maintenance windows on 19 and 24 September. The page holds imported records and its calendar loads in the browser, so 10 to 20 July could not be read (20). API limits published per plan, 100 requests a minute per token on Free Forever, Unlimited and Business, 1,000 on Business Plus and 10,000 on Enterprise, and MCP caps of 100 to 25,000 calls per rolling 24 hours (15). 429s carry `X-RateLimit-Limit`, `X-RateLimit-Remaining` and `X-RateLimit-Reset`, and MCP returns `RATE_LIMIT_EXCEEDED` with `retryAfter`. No backoff guidance and no idempotency keys found (9 of 15). No SLA found in the reviewed pages (0). Neither surface is marked beta, though the MCP docs say limits may change (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 5. Schema & documentation, 74 out of 100, up to 4.2 more on the total

Why it scored 74: OpenAPI 3.1 spec for API v2 with 138 operations and an OpenAPI 3.0 spec for v3 with 35, both public (25). The MCP tool schemas need an OAuth session and were not read. llms.txt and a Markdown copy of every docs page (10). 137 of 138 v2 operations carry a description, and the MCP tools page gives each tool one line and an example prompt. It lists Delete task while the MCP FAQ says no deletion tools exist (13 of 20). Required fields are marked, but v2 has 6 enums, dates are Unix milliseconds and `custom_fields` filters travel as JSON in a query string. v3 has 62 enums (10 of 15). Every v2 operation has a response example. Error responses are specified on few (400 on 6, 401 on 3), and the Common Errors page covers OAuth codes only (9 of 15). Versions sit in the path (v2, v3). No API changelog was found, developer.clickup.com/changelog returns 404, and the product changelog rarely covers the API (7 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 6. Maintenance & community, 54 out of 100, up to 4 more on the total

Why it scored 54: The MCP docs page was updated on 7 October 2026 and product Release Notes 4.08 are dated 18 September 2026 (30). The product changelog has three dated entries in the last 90 days (18 August, 25 August, 18 September), none about the public API, and docs pages changed on 10 August, 14 August, 17 September and 7 October (12 of 20). Public product changelog and feedback board, and 24/7 support stated on the pricing page. No API changelog, and response times were not checked (8 of 15). No entry under a ClickUp namespace among 13 ClickUp results in the official MCP registry, and no official SDK (0). The official clickup-plugin repository is MIT, at version 1.1.0, with six commits between 1 April and 7 September 2026 (4 of 10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 7. Transparency & trust, 75 out of 100, up to 2.2 more on the total

Made of editorial 52, provenance 97.

Why it scored 75: Closed service under Terms of Service effective 27 June 2025 and Developer Terms last updated 16 July 2024, naming Mango Technologies, Inc. DBA ClickUp. Clause 4.13(e) of the terms excludes API access with an unauthorised or third-party client, without defining it. The plugin repository is MIT (13 of 30). Privacy policy effective 2 June 2026 and a public DPA. Retention is stated as long as reasonably required, with no periods, and deletion at the end of term as soon as reasonably practicable. The security page says AI partners may not train on or retain customer data (18 of 30). No deprecation policy or dated notices found, and the Developer Terms state no obligation to maintain or support the API (3 of 20). Sub-processor list updated 28 September 2026 with purposes and locations, and Enterprise data residency in the US, Europe and Asia Pacific (18 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Terms of service: read, states 6 of the 7 things a reader expects, and has 1 clause that costs points (7.1 of 10)

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: the MCP tool definitions (input schemas, descriptions, readOnlyHint and destructiveHint), since tools/list needs an OAuth session. The tool count of 48 comes from the docs page
- unchecked: help.clickup.com, which answered with a bot check, so MCP admin controls, audit log contents and the add-on articles were not read
- unchecked: status history for 10 to 20 July 2026. The feed returns 25 records, most of them imported from 2018 and 2019, and the page calendar loads in the browser
- Whether the MCP server has a delete tool. The tools page lists Delete task and the MCP FAQ says no deletion tools exist
- Whether Free Forever signup asks for a card. We did not go through signup
- Whether any tier carries an uptime SLA. /terms/sla returned ClickUp's error page and none was found in the terms
- What clause 4.13(e) of the terms (no API access with an unauthorised or third-party client) means for agents using a personal token
- The MCP docs name Core, Business Plus and Enterprise Plus plans that the pricing page did not show on 8 October 2026
- Whether the read scope removes write tools from tools/list

## Weaknesses

- MCP calls are capped per rolling 24 hours without the Everything AI add-on, 100 on Free Forever and 300 on Unlimited, per Workspace and client
- Personal API tokens and REST OAuth tokens never expire and carry no scopes
- No API changelog or deprecation policy found, and the Developer Terms state no obligation to maintain the API
- No official SDK and no idempotency keys found, and no entry under a ClickUp namespace in the official MCP registry
- 48 documented MCP tools, and the tools page lists Delete task while the MCP FAQ says no deletion tools exist

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Connect to https://mcp.clickup.com/mcp with OAuth 2.1 and PKCE. API keys and REST OAuth tokens are refused on the MCP server
- Pass `workspace_id` on every MCP call when the user belongs to more than one Workspace, as ClickUp's own skills instruct
- Budget MCP calls. Each tool call counts against the rolling 24-hour cap, and `RATE_LIMIT_EXCEEDED` returns `retryAfter`
- On the REST API read `X-RateLimit-Remaining` and `X-RateLimit-Reset`, and page Get Tasks with `page` at 100 tasks a page
- Treat `team_id` in API v2 as the Workspace ID, and send dates as Unix milliseconds

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.