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

io.github.robertnowell/konid

NPM · KONID-AI · SCANNED AUG 3

Three translation options per phrase, casual to formal, with register context and audio.

Available components

+25 this week 63 Trust /100
Trust breakdown (6 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 →

Supply Chain Security88
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (141 of 142), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (141 of 142), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability71
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 592 tokens (~197/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 Management27
  • Stability observed for 8 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
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · konid-ai

# add to Claude Code
claude mcp add robertnowell-konid -- npx -y konid-ai
# add to Codex CLI
codex mcp add robertnowell-konid -- npx -y konid-ai
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "robertnowell-konid": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "konid-ai"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add robertnowell-konid --command npx --arg -y --arg konid-ai
# ~/.hermes/config.yaml
mcp_servers:
  robertnowell-konid:
    command: "npx"
    args: ["-y", "konid-ai"]
// mcp.json
{
  "mcpServers": {
    "robertnowell-konid": {
      "command": "npx",
      "args": [
        "-y",
        "konid-ai"
      ]
    }
  }
}
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.

  • 2 Aug 26 +49
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Security disclosure: unverified → fail functional
    • Schema quality: unverified → excellent functional
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Stability: unverified → 0.23 functional
    • Licence: MIT functional
  • 1 Aug 26 −6
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 31 Jul 26 −18
    • Malware scan: pass → unverified security
  • 29 Jul 26 +20
    • Tool coverage: unverified → 100 functional
  • 28 Jul 26 −20
    • Tool coverage: 100 → unverified functional
    • First check of Schema quality: unverified functional
  • 27 Jul 26 38

    First indexed and scored.

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 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 141 packages

141 packages in the resolved dependency tree · 138 deprecated · 39 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 3 exposed · ~306 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.

Tool Tokens
coach ~130

Express an idea naturally in a target language. Returns 3 socially-calibrated options with romanization, literal meanings, tone notes, and cultural context. Each option is numbered for use with the speak tool.

NameTypeReqDescription
contextstringSocial context: who you're talking to, the situation (e.g. 'texting a date', 'email to boss', 'casual with friends')
target_languagestringTarget language (e.g. 'Mandarin Chinese', 'Japanese', 'Korean', 'Spanish')
textstringyesThe idea you want to express (in English)

No output schema declared.

No examples provided.

replay ~35

Replay the last spoken audio clip. Use when the user says 'again', 'replay', 'repeat', or 'play it again'.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

speak ~141

Speak text aloud using text-to-speech. Generates audio and plays it through speakers. Use after coach to hear how a phrase sounds.

NameTypeReqDescription
meaningstringEnglish meaning of the text (e.g. 'thanks', 'thank you'). Include this so the output is understandable without context.
slowbooleanSpeak at a slower pace for clearer pronunciation
textstringyesThe text to speak (in the target language)
voicestringedge-tts voice name (e.g. 'zh-CN-YunjianNeural', 'zh-CN-XiaoxiaoNeural'). Auto-detected from text if omitted.

No output schema declared.

No examples provided.