Heads-up
NPM · HEADSUP-MCP
Spoken voice alerts on Mac, Linux and Windows when your coding agent finishes a task or needs you.
Available components
Last scanned (2 hours ago)
Scores higher than 36% of npm servers
Category Productivity and Notes
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 Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (GPL-3.0-only).Pass
- Actively maintained (last published 2 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability64
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 726 tokens (~726/item across 1 items; 1 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 Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage93
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 80% 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
- We read all 1 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 1 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
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.
- 3 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 2 Nov 26 54
First indexed and scored.
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 5 Nov 2026 · Analysed npm/headsup-mcp@1.7.0
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 →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
notify_user ~726
Play a short spoken alert on the user's computer speakers so they can come back to it. Call it once at the end of a turn (or when starting something long), picking the status that matches why you stopped: - completed: the task is done ("I've completed the task.") - review: work is ready for the user to review (diff, design, document) ("I need your review.") - feedback: you want the user's opinion on a draft or direction ("I need your feedback.") - input: you need information or a decision from the user ("I need your input.") - approval: you are waiting on a permission prompt or go-ahead ("I need your approval to continue.") - question: you have a short clarifying question ("I have a quick question for you.") - blocked: you cannot make progress without the user ("I'm stuck, and I need your help.") - error: an unexpected error or crash needs the user's attention ("Something went wrong. Please take a look.") - tests_passed: a test run finished green ("All the tests are passing.") - tests_failed: a test run finished with failures you could not fix ("Some tests are failing.") - deployed: a deploy or release succeeded ("The deployment is live.") - deploy_failed: a deploy or release failed ("The deployment failed.") - pr_ready: a PR is open and ready for the user ("The pull request is ready.") - next_task: you are idle and waiting for new work ("I'm ready for the next task.") - limit_warning: usage or quota is nearly used up ("I'm close to my usage limit.") - limit_reached: usage or quota is used up and work stopped ("I've hit my usage limit.") - sign_in: a login, OAuth or credential step needs the user ("I need you to sign in.") - long_task: you are starting something long and the user can step away ("This will take a while. I'll let you know when it's done.") - progress: a long task is still running ("Quick update. I'm still working on it.") - reminder: you asked for something earlier and are still waiting ("I'm still waiting on you.") Their settings (off switch, mute,…
| Name | Type | Req | Description |
|---|---|---|---|
| folder | string | – | The absolute path of the folder this work happened in. Pass it whenever that isn't the folder the session started in (you changed into another repo, or work in a subfolder of a parent like ~/Dev), so… |
| message | string | – | Optional: your own line, spoken instead of the status's fixed line when that line doesn't say enough (e.g. "The migration ran, but two tables need your review. Should I roll back or keep going?"). Pl… |
| repeat | integer | – | How many times to play the line (use 2 for something urgent). |
| status | string | yes | – |
| volume | integer | – | Optional target volume %. Leave it out: volume is handled automatically within their safety caps. |
No output schema declared.
No examples provided.
How do I install the Heads-up MCP server?
Heads-up runs locally as an npm package, launched with npx -y headsup-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 · headsup-mcp
claude mcp add abhishek207-headsup-mcp -- npx -y headsup-mcp
What is the Heads-up MCP server?
Heads-up is an MCP server listed in the public MCP registry as io.github.abhishek207/headsup-mcp. Spoken voice alerts on Mac, Linux and Windows when your coding agent finishes a task or needs you. This page covers its npm package (headsup-mcp).
Is the Heads-up MCP server safe to use?
Heads-up scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 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 Heads-up MCP server expose?
Heads-up exposes 1 tool: notify_user. Their descriptions and schemas cost roughly 726 tokens of context every time the server is loaded.
Is the Heads-up MCP server still maintained?
Heads-up is still listed as active in the MCP registry. We last reached this channel on 5 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 Heads-up MCP server under?
Heads-up declares the GPL-3.0-only licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.