TogglSAFE
MCP server for Toggl Track integration with intelligent caching and reporting tools
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Talk to your time tracking. Pull reports, start timers, inspect desktop activity, and turn raw Toggl data into useful recaps from Claude or any MCP-compatible client.
[](https://www.npmjs.com/package/@verygoodplugins/mcp-toggl) [](https://modelcontextprotocol.io) [](LICENSE) [](https://developers.track.toggl.com/docs/)
See What Your Week Actually Looked Like
You ask: "Give me the recap of my week"
The MCP server returns hydrated time entries with project, workspace, client, tag, and running-timer context. Your client can turn that into a readable recap:
32.7 hours across 31 entries and 7 projects. Monday was a light planning day, Tuesday had the long implementation block, Wednesday stayed focused on one project, and Friday turned into a shipping run. The top project took 27% of the week, with two smaller projects close behind.
The server does not hard-code this prose or chart. It exposes structured Toggl data in a shape that makes synthesis easy.
Catch the Drift
You ask: "Did I actually work on what I said I worked on for that PR review entry?"
toggl_get_timeline can compare a tracked entry boundary with Toggl Track Desktop activity:
The entry ran 1h 33m. About 67 minutes were in review tools, 5 minutes were scattered across chat apps, and the rest was idle or trimmed timeline space. The entry mostly checks out.
This is useful before invoicing, after long context-switching days, or whenever a vague entry like "admin" starts hiding too much Slack and browser time.
See Patterns Over Time
You ask: "Show me last month at a glance"
Daily and weekly report tools make it straigh
5c851c37d402OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-toggl -- npx -y @verygoodplugins/[email protected]
Exposed tools (15)
12 read · 2 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
toggl_cache_stats | read | Get cache statistics and performance metrics |
toggl_check_auth | read | Verify Toggl API connectivity and authentication is valid |
toggl_clear_cache | destructive | Clear all cached data |
toggl_daily_report | read | Generate a daily report with hours by project and workspace |
toggl_get_current_entry | read | Get the currently running time entry, if any |
toggl_get_time_entries | read | Get time entries with optional date range filters. Returns hydrated entries with project/workspace names. |
toggl_list_clients | read | List clients for a workspace |
toggl_list_projects | read | List projects for a workspace |
toggl_list_workspaces | read | List all available workspaces |
toggl_project_summary | read | Get total hours per project for a date range |
toggl_start_timer | write | Start a new time entry timer |
toggl_stop_timer | write | Stop the currently running timer |
toggl_warm_cache | read | Pre-fetch and cache workspace, project, client, and tag data for better performance |
toggl_weekly_report | read | Generate a weekly report with daily breakdown and project summaries |
toggl_workspace_summary | read | Get total hours per workspace for a date range |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
toggl_clear_cache
.release-please-manifest.json
@modelcontextprotocol/sdk, dotenv, node-fetch, zod, @eslint/js, @types/node, @vitest/coverage-v8, eslint
Gates applied: no_behavioural_pass.
5c851c37d402full audit observations/trust-audit/mcp-server/verygoodplugins__toggl-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 5c851c37d402 | SAFE | B | 89 | first audit |
Questions
What is the Toggl MCP server?
MCP server for Toggl Track integration with intelligent caching and reporting tools
What tools does Toggl expose?
15 in total: 12 read-only, 2 that write, and 1 that can delete or overwrite (toggl_clear_cache). Every one is listed on this page with its risk.
Is Toggl safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Toggl need?
It reads TOGGL_API_KEY, TOGGL_API_TOKEN and TOGGL_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Toggl run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @verygoodplugins/mcp-toggl at 1.1.0.
How current is this page?
The grade is for one exact copy of the source (5c851c37d402), read on 2026-10-08. The repository is watched and re-audited when it changes.