mcp-toggl AGENTS.md

mcp-toggl AGENTS.md is an instructions file for Codex, OpenCode from verygoodplugins/mcp-toggl. It costs 3,641 tokens per session, scanned C, original, MIT.

Development instructions for an MCP server that connects AI assistants to Toggl Track, a service for recording work time.

In plain words
What is it for?
Use it to develop or run tools for time entries, timers, daily or weekly reports, project and workspace hours, clients, and desktop activity data.
Why use it?
They explain how the server translates assistant requests into Toggl API calls and how its project data and reports are organized.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/verygoodplugins/mcp-toggl/agents-md
Clone the repo
git clone --depth 1 https://github.com/verygoodplugins/mcp-toggl

Made for: Codex, OpenCode.

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.

agentmods badge for mcp-toggl AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/verygoodplugins/mcp-toggl/agents-md.svg)](https://agentmods.dev/instructions/verygoodplugins/mcp-toggl/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/verygoodplugins/mcp-toggl/agents-md"><img src="https://agentmods.dev/badge/instructions/verygoodplugins/mcp-toggl/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,641 This file is loaded in full into every session.
When invoked 3,641 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.03641 $0.03641
Opus 5 $0.01820 $0.01820
Sonnet 5 $0.00728 $0.00728
Haiku 4.5 $0.00364 $0.00364

Measured 4d ago against content hash af3fa3b7cf9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

mcp-toggl AGENTS.md scanned grade C with 1 finding 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 4d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

The test runner is **Vitest** (`vitest run`). There is no separate integration-test suite — `npm test` runs the full suite and needs no Toggl credentials: HTTP is mocked (`node-fetch` is `vi.mock`-ed in `tests/toggl-api.
AGENTS.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to coding agents (Claude Code, Cursor, Codex, etc.) when working with this repository. It is the single source of truth; CLAUDE.md imports it via @AGENTS.md.

Project Overview

MCP Toggl is an MCP (Model Context Protocol) server for Toggl Track time tracking. It lets AI assistants read time entries, start/stop timers, generate daily/weekly/project/workspace reports, list workspaces/projects/clients, and inspect the Toggl Desktop activity timeline — translating MCP tool calls into Toggl Track API v9 requests over stdio.

Core purpose:

  • Translate MCP tool calls into Toggl Track API requests
  • Provide reporting (daily, weekly, per-project, per-workspace hour summaries)
  • Cache workspace/project/client/tag metadata to cut API calls and avoid rate limits

This is a single-package TypeScript project (ES modules, Node 20.19+/22.12+). It runs as a stdio MCP server; there are no hooks, queues, or background services.

Build & Development

# Install dependencies
npm install

# Development with hot-reload (tsx watch on src/index.ts)
npm run dev

# Build TypeScript to dist/ (removes dist first, then tsc; postbuild chmod +x dist/index.js)
npm run build

# Start the built server (stdio mode)
npm start

# Run tests (Vitest, single run — no watch)
npm test

# Tests with coverage (v8)
npm run test:coverage

# Lint (ESLint over src/ and tests/)
npm run lint

# Format (Prettier over src/**/*.ts)
npm run format

# First-time local setup helper (creates .env from .env.example, installs, builds)
npm run setup

The test runner is Vitest (vitest run). There is no separate integration-test suite — npm test runs the full suite and needs no Toggl credentials: HTTP is mocked (node-fetch is vi.mock-ed in tests/toggl-api.test.ts), so tests never hit the live API. npm run build does rm -rf dist && tsc, and a postbuild step marks dist/index.js executable so the mcp-toggl bin works.

Read the full file on GitHub · 225 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.

  1. 4d ago First seen · 225 lines · 3,641 tokens per session scan C af3fa3b7cf9d

Subscribe to this mod's changes

mcp-toggl AGENTS.md is an instructions file published in the GitHub repository verygoodplugins/mcp-toggl (33 stars, last pushed yesterday), licensed MIT. It adds 3,641 tokens to every session, about $0.0182 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.