three.ws Herald
NPM · @THREE-WS/HERALD-MCP
Tell your human in person: a 3D character walks onto their open browser tab and says it out loud.
Available components
Last scanned (21 hours ago)
Scores higher than 54% of npm servers
Category Communication
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 Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 30 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
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 (Apache-2.0).Pass
- Actively maintained (last published 42 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability66
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 880 tokens (~293/item across 3 items; 3 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 Management80
- Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 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
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.
- 24 Oct 26 −5
- CVE-2023-54404 affects this package: high ▼ security
- Known CVEs: pass → fail ▼ security
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.
- 21 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Oct 26 +6
- Stability: unverified → 0.43 ▲ functional
- 1 Oct 26 +15
- Malware scan: unverified → pass ▲ security
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 24 Oct 2026 · Analysed npm/@three-ws/herald-mcp@0.1.0
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 →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 30 |
| 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 →
announce Tell your human, in person ~371
Deliver one line to the human who owns this key, in person: their 3D companion walks onto the browser tab they have open, gestures, and says it, with an optional link to click through. Use this for the handful of moments that deserve to interrupt someone (a long task finished, a decision is needed, something broke), not for progress chatter: the client applies an importance floor, a rate limit, quiet hours and dedupe, so noise is dropped rather than queued. The message is always delivered to the key owner and nobody else. If no browser is open it expires quietly in about five minutes; the durable record is the notification inbox, not this. Returns the queued announcement and how long it stays deliverable.
| Name | Type | Req | Description |
|---|---|---|---|
| emote | string | – | Gesture the avatar arrives with. Rigs without it fall back to a wave. |
| from | string | – | Who it is from, spoken as attribution ("your build", "Stripe", the agent's name). |
| importance | integer | – | 0-100, default 70. The client drops anything under its floor (50 by default) and only lets 90+ through quiet hours. Use 90+ for something broken or blocking, 60-80 for a finished task, under 50 for s… |
| key | string | – | Dedupe key. Two announcements sharing a key are said once, so a retrying job can call this every attempt without repeating itself. |
| text | string | yes | The line to say out loud. One sentence. Write it as speech, not as a log line. |
| tone | string | – | Colours the bubble and picks a default gesture. Default alert. |
| url | string | – | Where clicking through goes: an absolute https URL or a three.ws path. |
No output schema declared.
No examples provided.
announce_result Report a finished task in person ~229
Tell the human how a task went, in person, with the urgency chosen for you from the outcome: `failed` and `needs_input` are loud enough to cut through quiet hours, `succeeded` is not. Pass the task name, the outcome, and optionally how long it took and where to look. This is the right tool at the end of anything long enough that the person walked away from it. Returns the queued announcement.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | One short clause of context ("3 tests failing", "waiting on your approval"). |
| key | string | – | Dedupe key, so a retry loop reporting the same result says it once. |
| outcome | string | yes | How it ended. Drives importance, tone and gesture. |
| seconds | number | – | How long it took, in seconds. Rendered as "in 4m" when given. |
| task | string | yes | What was being done, in human words ("the nightly backfill", "your test suite"). |
| url | string | – | Where to look: the run, the diff, the dashboard. |
No output schema declared.
No examples provided.
check_rail Check the delivery rail ~105
Verify that the configured key works and the delivery rail accepts announcements, without interrupting anybody: it queues a line at importance 0, which every client drops under its own floor. Use this once when wiring an agent up, or when announce fails and you need to tell a bad key apart from an unreachable rail. Returns the base URL and whether the credential was accepted.
| Name | Type | Req | Description |
|---|---|---|---|
| note | string | – | Optional label recorded on the probe, to tell two agents apart in a log. |
No output schema declared.
No examples provided.
How do I install the three.ws Herald MCP server?
three.ws Herald runs locally as an npm package, launched with npx -y @three-ws/herald-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 · @three-ws/herald-mcp
claude mcp add nirholas-herald-mcp -- npx -y @three-ws/herald-mcp
What is the three.ws Herald MCP server?
three.ws Herald is an MCP server listed in the public MCP registry as io.github.nirholas/herald-mcp. Tell your human in person: a 3D character walks onto their open browser tab and says it out loud. This page covers its npm package (@three-ws/herald-mcp).
Is the three.ws Herald MCP server safe to use?
three.ws Herald scores 75 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 24 October 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 three.ws Herald MCP server expose?
three.ws Herald exposes 3 tools: announce, announce_result, check_rail. Their descriptions and schemas cost roughly 705 tokens of context every time the server is loaded.
Is the three.ws Herald MCP server still maintained?
three.ws Herald is still listed as active in the MCP registry. We last reached this channel on 24 October 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 three.ws Herald MCP server under?
three.ws Herald declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.