What is mcp-timely CLAUDE.md?

A CLAUDE.md instruction file for the mcp-timely Python project, documenting development commands, authentication, server modes, testing, releases, and deployment.

Use it to run tests and linting, authenticate, start stdio or HTTP servers, use Docker Compose, and understand the automated release process.

It gives Claude Code the project-specific commands and conventions needed to test, format, run, release, and deploy the server consistently.

How CaseyRo/mcp-timely configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to CaseyRo/mcp-timely. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/CaseyRo/mcp-timely/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/CaseyRo/mcp-timely

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/caseyro/mcp-timely/claude-md/github.svg)](https://agentmods.dev/instructions/caseyro/mcp-timely/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/caseyro/mcp-timely/claude-md"><img src="https://agentmods.dev/badge/instructions/caseyro/mcp-timely/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/caseyro/mcp-timely/claude-md"><img src="https://agentmods.dev/badge/instructions/caseyro/mcp-timely/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,883 This file is loaded in full into every session.

When invoked 1,883 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01883	$0.01883
Opus 5.5	$0.00753	$0.00753
Sonnet 5.5	$0.00377	$0.00377
Haiku 4.5	$0.00188	$0.00188

Measured 12d ago against content hash 4e09d8348a4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-timely 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 12d 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.

CLAUDE.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

Dependencies are managed with uv. Python >= 3.12.

uv sync                                   # install deps (incl. dev group)
uv run pytest                             # full suite (in-memory MCP client, no network)
uv run pytest tests/test_session.py -k rotated   # single test by name
uv run ruff check .                       # lint
uv run ruff format .                      # format

uv run mcp-timely auth                    # one-time OAuth bootstrap (prints URL, takes OOB code)
uv run mcp-timely                         # run stdio server (default)
TRANSPORT=http MCP_API_KEY=dev uv run mcp-timely   # HTTP server on :8000 (/mcp, /health)

docker compose up                         # HTTP server on :8011 (maps to container :8000)

Git & release conventions

Releases are tag-only: any push to main that changes non-doc files triggers .github/workflows/release.yml, which runs tests + pip-audit, pushes the next vX.Y.Z tag (nothing is committed to the protected branch), builds/pushes a multi-arch image to ghcr.io/caseyro/mcp-timely with the tag baked in as APP_VERSION (what /health reports), then calls a signed deploy webhook so the host pulls the new image.

version in pyproject.toml is stale by design; the git tag is the version. Don't bump it.
Include [skip ci] in a commit message to skip the release.
Pure-markdown and tests/** changes don't trigger a release (paths-ignore).
A green run is not a release: confirm the v* tag appeared.
The deploy-webhook step is skipped when its repo secret is unset; when set, it must match the deploy target's webhook secret exactly (a mismatch fails with a 401).
Dependabot runs weekly (uv, docker, actions ecosystems) with auto-merge; each merged PR ships a release.

Architecture

FastMCP 4 server (src layout, src/mcp_timely/) exposing three question-shaped read tools plus four guarded write tools over Timely's API. No user/team parameters: everything is scoped to the authorized user (account + user id resolved lazily at first call and cached).

Read the full file on GitHub · 71 lines

Changes

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.

12d ago Changed · +1 lines · +122 tokens per session 4e09d8348a4b
27d ago Changed · +1 lines · +164 tokens per session 336c8754fca9
28d ago Changed · +27 tokens per session 77360eedba6b
1mo ago Changed · +1 lines · +189 tokens per session cec1f1b339d0
1mo ago Changed · +7 lines · +104 tokens per session e4da13f8d05d
2mo ago First seen · 61 lines · 1,277 tokens per session scan A e2ca3131ad1e

Subscribe to this mod's changes

mcp-timely CLAUDE.md is an instructions file published in the GitHub repository CaseyRo/mcp-timely (0 stars, last pushed 5d ago), licensed MIT. It adds 1,883 tokens to every session, about $0.0075 per session on Opus 5.5. 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 2026-08-31.

Python fastmcp mcp mcp-server time-tracking timely

mcp-timely CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-timely CLAUDE.mdCaseyRo/mcp-timely	Instructions file	0	5d ago	MIT	A	1,883	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-timely: Instructions file for Claude Code