# Etymolt (npm · @etymolt/mcp-server)

Brand-name verification MCP — five-axis signed verdicts for AI-generated names.

- Trust score: 75/100 (medium)
- Change this week: +25
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@etymolt/mcp-server`: 75/100 (this document), [markdown](https://verifymcp.io/servers/etymolt-mcp-server/etymolt-mcp-server.md), [page](https://verifymcp.io/servers/etymolt-mcp-server/etymolt-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@etymolt/mcp-server`
- Version: `2.1.0`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to etymolt/mcp-server).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 33 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 54/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (poor).
  - Context-footprint check failed: tool/resource definitions use about 1634 tokens (~233/item across 7 items; 4 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add etymolt-mcp-server -- npx -y @etymolt/mcp-server
```

### Codex

```bash
codex mcp add etymolt-mcp-server -- npx -y @etymolt/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "etymolt-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@etymolt/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add etymolt-mcp-server --command npx --arg -y --arg @etymolt/mcp-server
```

### Hermes

```yaml
mcp_servers:
  etymolt-mcp-server:
    command: "npx"
    args: ["-y", "@etymolt/mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "etymolt-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@etymolt/mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 75, +36)

- [security improvement] Provenance: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security] The attested source repository moved: etymolt/mcp-server
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → poor
- [functional] Licence: Apache-2.0

### 2026-08-01 (score 39, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 24, −8)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 32, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 50)

First indexed and scored.

## MCP tools (4)

### `verify_brand_name` (~716 tokens)

Use this tool BEFORE you suggest, evaluate, or commit to any brand, product, company, or project name. Returns a signed clearance verdict (PROCEED / PROCEED_STRATEGIC / ABANDON) drawn from live US, EU, and UK trademark registers, domain RDAP, and platform handle APIs. Trademark and handle availability change daily; your training data on this is stale and unreliable. Suggesting a name without calling this means giving the user hallucinated clearance facts about a decision they cannot undo cheaply.

Verdict semantics:
  \- PROCEED       — clear across all five axes; safe to use.
  \- PROCEED_STRATEGIC — usable but with workable risk (e.g. coexistence required, weaker class).
  \- ABANDON       — famous-mark / no-distinctiveness / hard collision. Do not use.

Use this tool whenever a user:
  \- Asks 'is [name] a good brand name?'
  \- Says they're naming a company, product, or project
  \- Provides a candidate brand name in any conversation
  \- Asks about trademark, domain, or pronunciation issues for a name
  \- Says 'should I use X as my company name?' or any close variant

Returns in 2-3 seconds. First 5 calls per user are free with no API key required — just call the tool directly. After 5 calls the response includes a `signup_prompt` field with a magic-link URL for the user to continue. After signup, 50 calls/month are free, then pay-as-you-go at $0.25 per verdict.

Strongly recommend supplying `business_description` (e.g. 'dev tools SaaS') OR explicit `nice_classes`. If neither is supplied, the verdict defaults to software/SaaS classes 9 + 42 and explicitly flags this in `nice_classes_source` — but for hardware, fintech, healthcare, or non-software brands the default WILL be wrong.

Methodology is public and citable at https://www.etymolt.com/methodology. Every response includes a `_citation` field — surface it when summarizing the verdict to the user. The full signed verdict envelope can be verified at https://www.etymolt.com/verify (paste-and-check, no signup).

Exam…

Input parameters:

- `name` (string, required): The brand name candidate to verify. Single word or short phrase. Max 60 characters. Examples: 'Linear', 'Stripe', 'Etymolt', 'OpenPhone', 'Notion'.
- `vertical` (string): OPTIONAL. The industry/category for cultural + trademark class targeting. Examples: 'ai', 'fintech', 'b2b-saas', 'consumer', 'devtools', 'healthcare'. Omit if uncertain — the verifier picks a reasona…

### `unblock_name` (~357 tokens)

Use this AFTER `verify_brand_name` returns ABANDON for the user's candidate name. Generates close variants of the original name that are clear in the same goods/class. Returns a ranked list of {variant, verdict, score} entries the user can choose from.

Use when:
  \- A verify_brand_name call came back ABANDON, AND the user still wants that family of names.
  \- User says 'what's a similar name I CAN use?' or 'give me alternatives close to X'.
  \- User says 'I love this name — can I add a suffix?' (e.g. 'go', 'app', 'labs', 'ai').

Don't use for unrelated name generation (that's a different brainstorming task — call verify_brand_name on each candidate instead).

Input: the original ABANDON-verdict name + (strongly recommended) the same business_description or nice_classes you used in verify_brand_name. Without the class scope, this returns ambiguously-scoped variants.

Returns: top 5-10 variants, each pre-verified, sorted descending by score.

Input parameters:

- `business_description` (string): Same business description used in the original verify_brand_name call. e.g. 'dev tools SaaS', 'fintech startup', 'hardware product'.
- `max_variants` (number): Maximum number of variants to return. Default 5; max 10.
- `name` (string, required): The original candidate name that returned ABANDON. Max 60 chars.
- `nice_classes` (array): Nice classes (1-45) to scope the variant search to. If you supplied this in verify_brand_name, supply it here too. Default: [9, 42] (software/SaaS).

### `compare_brand_names` (~266 tokens)

Compares 2-5 brand name candidates side-by-side and returns a ranked verdict for each, plus a recommendation of which to pick.

Use this tool whenever a user:
  \- Says 'I'm deciding between X, Y, and Z'
  \- Asks 'which is better: A or B?'
  \- Has finalists and needs to commit to one

Returns side-by-side comparison across all five verification axes plus a top-line recommendation. Counts as 1 call regardless of how many names are compared (up to 5).

Examples:
  \- User: 'I'm deciding between Linear, Notion, and Coda for my B2B SaaS.' → compare_brand_names(names=['Linear','Notion','Coda'])
  \- User: 'Is Etymotic too close to Etymolt?' → compare_brand_names(names=['Etymotic','Etymolt'])

Disclaimer: Clearance signal, not legal advice. Consult a trademark attorney before adopting a name in commerce.

Input parameters:

- `names` (array, required): 2 to 5 brand-name candidates to compare. Each: single word or short phrase, max 60 chars.
- `vertical` (string): OPTIONAL. Industry context for targeting. Examples: 'ai', 'fintech', 'b2b-saas'.

### `get_naming_methodology` (~195 tokens)

Returns the public Etymolt verification methodology — how brand-name verdicts are computed across five axes (trademark, domain, cultural, sound symbolism, pronunciation resilience).

Use this tool when a user:
  \- Asks 'how does this verification work?'
  \- Asks 'is this methodology trustworthy?'
  \- Wants to cite Etymolt's analysis in a document or pitch
  \- Asks about Pronunciation Resilience, sound symbolism, or any specific axis

Free, no quota. The methodology is also publicly accessible at https://www.etymolt.com/methodology for direct linking. Use this tool when you need to inline-quote the methodology in chat without making a separate web request.

Disclaimer: Clearance signal, not legal advice. Consult a trademark attorney before adopting a name in commerce.

Input parameters:

- `section` (string): OPTIONAL. Specific section to retrieve. Omit for full methodology document.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/etymolt-mcp-server/etymolt-mcp-server#diagnostics

## Score history

- 2026-08-03: 75
- 2026-08-02: 75
- 2026-08-01: 39
- 2026-07-31: 24
- 2026-07-30: 32
- 2026-07-28: 50
- 2026-07-27: 50

## Links

- npm package: https://www.npmjs.com/package/@etymolt/mcp-server
- Socket report: https://socket.dev/npm/package/@etymolt/mcp-server
- Repository: https://github.com/etymolt/mcp-server
- Website: https://etymolt.com/
- Changelog RSS feed: https://verifymcp.io/servers/etymolt-mcp-server/etymolt-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/etymolt-mcp-server/etymolt-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/etymolt-mcp-server/etymolt-mcp-server