three.ws Concierge
NPM · @THREE-WS/CONCIERGE-MCP
Ask any website's AI concierge a grounded question, and generate the embed to add one to a site.
Available components
Last scanned (15 hours ago)
Scores higher than 56% of npm servers
Category AI and Machine Learning
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
- 31 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 70 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability62
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 936 tokens (~312/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 Management100
- No destabilizing schema changes in the last 30 days.Pass
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
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
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 →
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.
- 20 Nov 26 0
- Stability: 0.97 → pass security
- 19 Nov 26 0
- Stability: pass → 0.97 functional
- 13 Nov 26 0
- Stability: 0.97 → pass security
- 12 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Nov 26 +5
- Source repository: unverified → pass ▲ security
- 8 Nov 26 −4
- Provenance: pass → unverified ▼ security
- 6 Nov 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.
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/@three-ws/concierge-mcp@0.1.1
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 | 31 |
| 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 →
concierge_ask Ask a website's AI concierge a question ~270
Ask an AI concierge a question and get a grounded answer. Provide a "url" and it fetches that page and answers using its real content (title, headings, navigation, main text), the way to ask any website a question. Or skip the url and pass "knowledge"/"content" to answer grounded in text you already have. The model is instructed not to invent facts it cannot see. Runs on the free three.ws lane; no key required.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | – | Raw page/document text to ground the answer in when you are not passing a url. |
| knowledge | string | – | Curated authoritative facts (FAQ, pricing, policies) to ground the answer in. Leads over harvested page text. |
| lang | string | – | BCP-47 language hint for the reply, e.g. "en", "es". |
| persona | string | – | Optional tone instruction for the reply, e.g. "concise and technical". |
| question | string | yes | The question to ask, in natural language. |
| siteName | string | – | Display name of the site/product (used in the answer's framing). Inferred from the page when omitted. |
| url | string | – | A web page to ground the answer in. It is fetched and its readable text is harvested. |
No output schema declared.
No examples provided.
concierge_avatars List available Concierge avatars ~59
List the rigged 3D avatars a three.ws Concierge widget can wear (id, name, personality tagline, style). Use the id with concierge_embed's "avatar" option, or omit it to let each visitor pick their own. Offline.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
concierge_embed Generate a Concierge embed snippet for a website ~438
Generate ready-to-paste embed code for adding a three.ws Concierge (an AI chat widget with a talking 3D avatar) to a website. Returns every install flavor by default (flavor "all"): the one-tag <script> install, the <three-concierge> web component, the npm snippet, and the imperative mount() call; pass `flavor` to get just one. Configure the accent color, avatar, greeting, curated knowledge, suggested prompts, position and theme. Offline: this only composes the code, it installs nothing.
| Name | Type | Req | Description |
|---|---|---|---|
| accent | string | – | CSS color that restyles the whole widget, e.g. "#f97316". |
| avatar | string | – | Initial avatar id: sol, nova, vera, atlas, echo. Omit to let the visitor pick. |
| customAvatar | string | – | URL of your own rigged GLB avatar (replaces the catalog). |
| endpoint | string | – | Custom answer endpoint. Omit to use the free hosted three.ws lane. |
| flavor | string | – | Which snippet(s) to return. "script" is the one-tag CDN install; "all" returns every flavor. |
| greeting | string | – | First line shown in the empty state and teaser bubble. |
| knowledge | string | – | Curated facts (FAQ, pricing, policies) the answers are grounded in. |
| lang | string | – | BCP-47 language hint for voice and replies. |
| muted | boolean | – | Start with voice output off. |
| noPicker | boolean | – | Hide the avatar picker. |
| noTeaser | boolean | – | Never show the proactive teaser bubble. |
| open | boolean | – | Start with the panel open. |
| persona | string | – | One-line tone instruction, e.g. "warm, playful, concise". |
| position | string | – | Corner the launcher docks to. |
| siteName | string | – | Name of the site/product, used in the greeting + grounding. |
| suggestions | array | – | Up to 4 suggested prompt chips. |
| theme | string | – | Color theme. "auto" follows the visitor's system/site. |
No output schema declared.
No examples provided.
How do I install the three.ws Concierge MCP server?
three.ws Concierge runs locally as an npm package, launched with npx -y @three-ws/concierge-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/concierge-mcp
claude mcp add nirholas-concierge-mcp -- npx -y @three-ws/concierge-mcp
What is the three.ws Concierge MCP server?
three.ws Concierge is an MCP server listed in the public MCP registry as io.github.nirholas/concierge-mcp. Ask any website's AI concierge a grounded question, and generate the embed to add one to a site. This page covers its npm package (@three-ws/concierge-mcp).
Is the three.ws Concierge MCP server safe to use?
three.ws Concierge scores 77 out of 100 on VerifyMCP. We recorded 1 known advisory 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 three.ws Concierge MCP server expose?
three.ws Concierge exposes 3 tools: concierge_ask, concierge_embed, concierge_avatars. Their descriptions and schemas cost roughly 767 tokens of context every time the server is loaded.
Is the three.ws Concierge MCP server still maintained?
three.ws Concierge 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 three.ws Concierge MCP server under?
three.ws Concierge 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.
What did VerifyMCP test on the three.ws Concierge MCP server?
VerifyMCP ran 16 checks on three.ws Concierge, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. 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.