Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Toggl 2.0

NPM · @TOGGLHQ/MCP · 2 COMPONENTS

Toggl 2.0 MCP server for tasks, projects, time entries, and workspace operations.

+15 this week 69 Trust /100

Last scanned (13 hours ago)

Scores higher than 39% of npm servers

Category Productivity and Notes

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security95
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known medium-severity CVE affects @opentelemetry/core 2.6.1, reached via @sentry/node > @opentelemetry/instrumentation-http > @opentelemetry/core. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 5 of 76 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency6
Schema Quality & AI Usability47
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 27189 tokens (~468/item across 58 items; 58 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage88
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 63% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 59 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (15)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +24
    • Known CVEs: unverified → fail ▼ security
    • Malware scan: unverified → pass ▲ security
    • Dependency health: unverified → 0.98 ▲ functional
    • Package version: 1.13.352 → 1.13.354 functional
    • Package version: 1.13.352 → 1.13.353 functional
  • 20 Nov 26 −24
    • Malware scan: pass → unverified ▼ security
    • Stability: pass → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Known CVEs: fail → unverified ▼ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Dependency health: 0.98 → unverified ▼ functional
    • Package version: 1.13.332 → 1.13.352 functional
    • Package version: 1.13.332 → 1.13.351 functional
    • Package version: 1.13.332 → 1.13.348 functional
    • Package version: 1.13.332 → 1.13.346 functional
    • Package version: 1.13.332 → 1.13.342 functional
    • Package version: 1.13.332 → 1.13.340 functional
    • Package version: 1.13.332 → 1.13.339 functional
    • Package version: 1.13.332 → 1.13.334 functional
    • Package version: 1.13.332 → 1.13.333 functional
  • 19 Nov 26 +24
    • Known CVEs: unverified → fail ▼ security
    • Stability: pass → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Malware scan: unverified → pass ▲ security
    • Tool coverage: 100 → unverified ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • Dependency health: unverified → 0.98 ▲ functional
    • Package version: 1.13.311 → 1.13.332 functional
    • Package version: 1.13.311 → 1.13.331 functional
    • Package version: 1.13.311 → 1.13.330 functional
    • Package version: 1.13.311 → 1.13.329 functional
    • Package version: 1.13.311 → 1.13.328 functional
    • Package version: 1.13.311 → 1.13.327 functional
    • Package version: 1.13.311 → 1.13.325 functional
    • Package version: 1.13.311 → 1.13.322 functional
    • Package version: 1.13.311 → 1.13.321 functional
    • Package version: 1.11.218 → 1.13.320 functional
    • Package version: 1.13.311 → 1.13.319 functional
    • Package version: 1.13.311 → 1.13.317 functional
    • Package version: 1.13.311 → 1.13.316 functional
    • Package version: 1.13.311 → 1.13.314 functional
    • Package version: 1.13.311 → 1.13.313 functional
    • Package version: 1.13.311 → 1.13.312 functional
  • 18 Nov 26 −9
    • Known CVEs: fail → unverified ▼ security
    • Malware scan: unverified → pass ▲ security
    • Dependency health: 0.98 → unverified ▼ functional
    • Package version: 1.13.294 → 1.13.311 functional
    • Package version: 1.13.294 → 1.13.310 functional
    • Package version: 1.13.294 → 1.13.309 functional
    • Package version: 1.13.294 → 1.13.306 functional
    • Package version: 1.13.294 → 1.13.305 functional
    • Package version: 1.13.294 → 1.13.304 functional
    • Package version: 1.13.294 → 1.13.302 functional
    • Package version: 1.13.294 → 1.13.301 functional
    • Package version: 1.13.294 → 1.13.300 functional
    • Package version: 1.13.294 → 1.13.299 functional
    • Package version: 1.13.294 → 1.13.298 functional
    • Package version: 1.13.294 → 1.13.297 functional
    • Package version: 1.13.294 → 1.13.296 functional
  • 17 Nov 26 −6
    • Known CVEs: unverified → fail ▼ security
    • Malware scan: pass → unverified ▼ security
    • Dependency health: unverified → 0.98 ▲ functional
    • Package version: 1.13.293 → 1.13.294 functional
  • 16 Nov 26 +6
    • Tool safety: pass → unverified ▼ security
    • Stability: pass → unverified ▼ security
    • Known CVEs: fail → unverified ▼ security
    • Malware scan: unverified → pass ▲ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Dependency health: 0.98 → unverified ▼ functional
    • Package version: 1.13.283 → 1.13.293 functional
    • Package version: 1.13.283 → 1.13.292 functional
    • Package version: 1.13.283 → 1.13.291 functional
    • Package version: 1.13.283 → 1.13.289 functional
    • Package version: 1.13.283 → 1.13.286 functional
    • Package version: 1.11.218 → 1.13.285 functional
    • Package version: 1.13.283 → 1.13.284 functional
  • 15 Nov 26 0
    • Malware scan: unverified → pass ▲ security
    • Package version: 1.13.281 → 1.13.283 functional
  • 14 Nov 26 +9
    • CVE-2026-128080 affects this package: medium ▼ security
    • Known CVEs: unverified → fail ▼ security
    • Malware scan: unverified → pass ▲ security
    • Dependency health: unverified → 0.98 ▲ functional
    • Package version: 1.13.280 → 1.13.281 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/@togglhq/mcp@1.13.354

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 4 findings
ID CVE Severity Vector Fix available
GHSA-8988-4f7v-96qf CVE-2026-54285 medium CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L yes
GHSA-3v2p-hm54-8qcq CVE-2026-128080 medium CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:N/A:N yes
GHSA-qqmp-wf37-98f9 CVE-2026-104872 medium CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:N/A:N yes
GHSA-g3hv-75wg-m249 CVE-2026-118764 medium yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 76 packages
Packages resolved 76
Stale 5
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 58 exposed · ~23,826 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
users ~426

Manage Focus users with the following actions: - **list**: Lists organization users (members). Use returned IDs for assignee_user_ids on tasks. Invite or provision new users from the Toggl Track/Focus web UI or billing admin — this API lists existing users only. (data: page, per_page, filter, sort_dir, only_admins, include_working_hours, include_rates, workspaces, tag_ids, roles, active_status, groups, pinned_ids, user_account_ids, org_user_ids) - **settings-email-unsubscribe** (data: token*) - **settings-email-unsubscribe-page** (data: token*) - **settings-get-desktop** (data: none) - **settings-get-landing-workspace** (data: first_launch) - **settings-list** (data: none) - **settings-partial-update** (data: payload*{...}) - **settings-record-workspace-opened** (data: none) - **settings-update-desktop** (data: payload*{desktop_autotracker_enabled, desktop_autotracker_focus_duration_enabled, desktop_autotracker_focus_duration_secs, desktop_autotracker_rules, desktop_autotracker_stop_on_no_match}) Pass the action-specific fields under `data` (required fields are marked with *). Mutations require a confirm_token handshake: call without confirm_token first to receive a token, then call again with the token to confirm. Optional dry_run: true validates input and returns { dry_run, operation, input } without calling the API.

NameTypeReqDescription
actionstringyesOne of: list, settings-email-unsubscribe, settings-email-unsubscribe-page, settings-get-desktop, settings-get-landing-workspace, settings-list, settings-partial-update, settings-record-workspace-open…
confirm_tokenstring–Mutation confirmation token from previous call
data––Action-specific payload. See each action's parameters in this tool's description; pass dry_run: true to validate it without calling the API.
dry_runboolean––

No output schema declared.

No examples provided.

version ~183

Manage Focus version with the following actions: - **service**: MCP package version plus the Focus API service revision. mcp.package is this published MCP package version (e.g. 1.8.0). focus_api is the Focus API process revision (git SHA / build number) — it does not change when you update the npm MCP package. (data: none) Pass the action-specific fields under `data` (required fields are marked with *). Mutations require a confirm_token handshake: call without confirm_token first to receive a token, then call again with the token to confirm. Optional dry_run: true validates input and returns { dry_run, operation, input } without calling the API.

NameTypeReqDescription
action–yes–
confirm_tokenstring–Mutation confirmation token from previous call
dataobject––
dry_runboolean––

No output schema declared.

No examples provided.

work-preparation ~128

Manage Focus work-preparation with the following actions: - **get** (data: page) Pass the action-specific fields under `data` (required fields are marked with *). Mutations require a confirm_token handshake: call without confirm_token first to receive a token, then call again with the token to confirm. Optional dry_run: true validates input and returns { dry_run, operation, input } without calling the API.

NameTypeReqDescription
action–yes–
confirm_tokenstring–Mutation confirmation token from previous call
dataobject––
dry_runboolean––

No output schema declared.

No examples provided.

working-hours ~242

Manage Focus working-hours with the following actions: - **create-for-user** (data: payload*, user_id*) - **delete-for-user** (data: payload*, user_id*) - **get-for-user** (data: user_id*) - **replace-working-hours-for-users** (data: payload*{schedule*, user_ids*}) - **update-for-user** (data: payload*, user_id*) Pass the action-specific fields under `data` (required fields are marked with *). Mutations require a confirm_token handshake: call without confirm_token first to receive a token, then call again with the token to confirm. Optional dry_run: true validates input and returns { dry_run, operation, input } without calling the API.

NameTypeReqDescription
actionstringyesOne of: create-for-user, delete-for-user, get-for-user, replace-working-hours-for-users, update-for-user
confirm_tokenstring–Mutation confirmation token from previous call
data––Action-specific payload. See each action's parameters in this tool's description; pass dry_run: true to validate it without calling the API.
dry_runboolean––

No output schema declared.

No examples provided.

workspace ~125

Manage Focus workspace with the following actions: - **get-context** (data: none) Pass the action-specific fields under `data` (required fields are marked with *). Mutations require a confirm_token handshake: call without confirm_token first to receive a token, then call again with the token to confirm. Optional dry_run: true validates input and returns { dry_run, operation, input } without calling the API.

NameTypeReqDescription
action–yes–
confirm_tokenstring–Mutation confirmation token from previous call
dataobject––
dry_runboolean––

No output schema declared.

No examples provided.

workspace-list ~41

List workspaces for the active MCP profile. Pass refresh: true to refetch from Accounts when a workspace is missing from cache.

NameTypeReqDescription
refreshboolean––

No output schema declared.

No examples provided.

workspace-settings ~441

Manage Focus workspace-settings with the following actions: - **workspace-settings-list**: List user workspace settings. (data: none) - **workspace-settings-partial-update**: Update user workspace settings. (data: payload*{has_opened_focus, onboarding_intent, onboarding_invited_user_ids, onboarding_project_id, onboarding_step, onboarding_task_id, onboarding_team_size, work_introduction_dismissed}) - **get-user-permissions** (data: none) - **get-workspace-currency** (data: none) - **get-workspace-export-branding** (data: none) - **get-workspace-invoice-watermark** (data: none) - **get-workspace-watermark** (data: none) - **list** (data: none) - **update** (data: payload*{archival_period_months, default_private, settings}) - **update-workspace-currency** (data: payload*{currency*}) - **update-workspace-invoice-watermark** (data: payload*{show_invoice_watermark*}) - **update-workspace-watermark** (data: payload*{show_watermark*}) Pass the action-specific fields under `data` (required fields are marked with *). Mutations require a confirm_token handshake: call without confirm_token first to receive a token, then call again with the token to confirm. Optional dry_run: true validates input and returns { dry_run, operation, input } without calling the API.

NameTypeReqDescription
actionstringyesOne of: workspace-settings-list, workspace-settings-partial-update, get-user-permissions, get-workspace-currency, get-workspace-export-branding, get-workspace-invoice-watermark, get-workspace-waterma…
confirm_tokenstring–Mutation confirmation token from previous call
data––Action-specific payload. See each action's parameters in this tool's description; pass dry_run: true to validate it without calling the API.
dry_runboolean––

No output schema declared.

No examples provided.

workspace-switch ~44

Switch the active workspace by updating the stored configuration. The new workspace takes effect on the next tool call. Use workspace-list to see available workspace IDs.

NameTypeReqDescription
workspace_id–yes–

No output schema declared.

No examples provided.

Install

How do I install the Toggl 2.0 MCP server?

Toggl 2.0 runs locally as an npm package, launched with npx -y @togglhq/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @togglhq/mcp

# add to Claude Code
claude mcp add toggl-toggl-mcp -- npx -y @togglhq/mcp
Common questions

What is the Toggl 2.0 MCP server?

Toggl 2.0 is an MCP server listed in the public MCP registry as io.github.toggl/toggl-mcp. Toggl 2.0 MCP server for tasks, projects, time entries, and workspace operations. This page covers its npm package (@togglhq/mcp).

Is the Toggl 2.0 MCP server safe to use?

Toggl 2.0 scores 69 out of 100 on VerifyMCP. We recorded 4 known advisories against it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Toggl 2.0 MCP server expose?

Toggl 2.0 exposes 58 tools: workspace-list, workspace-switch, profile-list, profile-switch, profile-remove, and 53 more. Their descriptions and schemas cost roughly 23,826 tokens of context every time the server is loaded.

Is the Toggl 2.0 MCP server still maintained?

Toggl 2.0 is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Toggl 2.0 MCP server under?

Toggl 2.0 declares the UNLICENSED licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.

What did VerifyMCP test on the Toggl 2.0 MCP server?

VerifyMCP ran 15 checks on Toggl 2.0, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Toggl 2.0: Security disclosure. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.