Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/npab19/clickup-mcp/claude-mdgit clone --depth 1 https://github.com/Npab19/clickup-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/npab19/clickup-mcp/claude-md)<a href="https://agentmods.dev/instructions/npab19/clickup-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/npab19/clickup-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02722 | $0.02722 |
| Opus 5 | $0.01361 | $0.01361 |
| Sonnet 5 | $0.00544 | $0.00544 |
| Haiku 4.5 | $0.00272 | $0.00272 |
Grade A, and why
clickup-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — ClickUp MCP Server
Notes for working on this codebase.
What this is
A multi-user MCP server for ClickUp. Pattern B (Python + FastMCP + OAuth
delegation) from ../General.Claude.md, extended with the per-identity governance
layer from ../CW Manage 3/src/middleware/.
Reference implementations, and what each contributes:
../Whoop/— OAuth delegation mechanics, client shape,transform.py, Docker layout. Single-user; do not copy its token handling.../CW Manage 3/src/middleware/— genuinely multi-user.policy-gate.ts,audit-capture.ts,rate-limit.ts,identity-resolver.tsare the originals for this server'spolicy.py,audit.py,rate_limit.py,context.py. Note thatGeneral.Claude.mdfiles it under "Pattern A: TypeScript + API Key", which badly undersells it.
The one rule
Never introduce process-global state keyed on anything but grant id.
The whole design turns on context.current_client() resolving the calling user's
token per request. Three things must stay namespaced by grant:
ClickUpClient._caches— an un-namespaced cache serves user A's tasks to user Brate_limit._buckets- everything written to
audit_log
tests/test_isolation.py is the gate. Run it before and after any change to
store.py, client.py, context.py, or oauth_provider.py.
ClickUp API facts that trip people up
- The v3 spec is ~20% of the API. Chat, Docs, audit logs, and a few strays.
Tasks/Lists/Spaces/Folders/time tracking/comments/custom fields are v2 only.
Both specs are vendored:
ClickUp_PUBLIC_API_V3.yaml(35 ops) andclickup-api-v2-reference.json(137 ops). - No PKCE, no scopes on ClickUp's side. Do not add them back to
oauth_provider.authorize(). - No refresh token, tokens never expire. There is deliberately no refresh path
in
client.py. A 401 with anOAUTH_*ECODE means revoked → prompt re-auth. A 401 with any other code is a permissions error and must NOT be reported as a dead token (_looks_like_bad_tokendraws that line). - Rate limit is per token = per user. 100/min on most plans.
- The v2 spec has wrong types —
time_spent/time_estimateare declaredstring|nullbut come back as integers. Don't codegen models from it. - "Team" means Workspace in the v2 API. Tools expose it as
workspace_id; paths useteam_id._common.client_and_workspace()does the mapping and fills in the default when the user has exactly one Workspace. - User Groups are also called "Teams" in ClickUp's UI. Different thing. See
tools/groups.py. - Folderless Lists still carry a
folderobject — a placeholder{"name": "hidden", "hidden": true}, not an omission. Read it naively and you report a folder named "hidden"; that was 54 of the first 100 live tasks. Usetransform._folder_name(), which checks the flag. - A task's
spacehas only an id, no name — hence thespace_idkey. - Task payloads are ~11 KB each. One 100-task page measured 1.12 MB raw versus
41 KB summarized.
raw=Trueon a list query is a context-window hazard; say so when a tool offers it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 224 lines · 2,722 tokens per session scan A 9254ef1c8061
clickup-mcp CLAUDE.md is an instructions file published in the GitHub repository Npab19/clickup-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,722 tokens to every session, about $0.0136 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other instructions, from other repositories
aipod CLAUDE.md
Claude Code instructions for bigg01/aipod, covering claude.md, what this project is, commands, architecture and server mode — src/aipod/server/.
fastmcp CLAUDE.md
Claude Code instructions for PrefectHQ/fastmcp, covering fastmcp development guidelines, required development workflow, repository structure, core mcp objects and development rules.
unraid CLAUDE.md
Claude Code instructions for dinglebear-ai/unraid, covering claude.md, what this is, identity and history (read before touching any url), "unraid-mcp" means five different things and agent plugins ship no claude code hooks.
archhub-mcp CLAUDE.md
Claude Code instructions for chrisryugj/archhub-mcp, covering archhub-mcp — 프로젝트 메모, 구조, 핵심 설계 결정, 검증 and in-memory mcp client로 도구 목록 + 실호출.
payload-mcp-oauth CLAUDE.md
Claude Code instructions for BrainWeb/payload-mcp-oauth, covering claude.md, project overview, repository structure, commands and install (run once at root).
swag-mcp CLAUDE.md
Claude Code instructions for jmagar/swag-mcp, covering swag mcp - claude memory reference, project overview, core architecture, key components and common development commands.