# io.github.smigolsmigol/llmkit (npm · @f3d1/llmkit-mcp-server)

AI cost tracking: 11 tools for spend, budgets, and Claude Code + Cursor + Cline costs

- Trust score: 64/100 (medium)
- Change this week: +14
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@f3d1/llmkit-mcp-server`: 64/100 (this document), [markdown](https://verifymcp.io/servers/smigolsmigol-llmkit/f3d1-llmkit-mcp-server.md), [page](https://verifymcp.io/servers/smigolsmigol-llmkit/f3d1-llmkit-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@f3d1/llmkit-mcp-server`
- Version: `0.4.7`
- 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**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), 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 (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 124 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 69/100
  - 75% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 383 tokens (~31/item across 12 items; 11 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

**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.

## Install

### Claude

```bash
claude mcp add smigolsmigol-llmkit -- npx -y @f3d1/llmkit-mcp-server
```

### Codex

```bash
codex mcp add smigolsmigol-llmkit -- npx -y @f3d1/llmkit-mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "smigolsmigol-llmkit": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@f3d1/llmkit-mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add smigolsmigol-llmkit --command npx --arg -y --arg @f3d1/llmkit-mcp-server
```

### Hermes

```yaml
mcp_servers:
  smigolsmigol-llmkit:
    command: "npx"
    args: ["-y", "@f3d1/llmkit-mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "smigolsmigol-llmkit": {
      "command": "npx",
      "args": [
        "-y",
        "@f3d1/llmkit-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 64, +25)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 75 → unverified
- [functional improvement] Schema quality: unverified → good
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional] First check of Capabilities: pass
- [functional] Licence: MIT

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

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 24, −26)

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

### 2026-07-30 (score 50, +26)

- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 75

### 2026-07-28 (score 24, −26)

- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 75 → unverified

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

First indexed and scored.

## MCP tools (11)

### `llmkit_usage_stats` (~37 tokens)

Get usage statistics (spend, requests, top models) for a time period

Input parameters:

- `period` (string): Time period

Output parameters:

- `cacheHitRate` (number)
- `cacheReadTokens` (number)
- `inputTokens` (number)
- `outputTokens` (number)
- `period` (string)
- `requests` (number)
- `topModels` (array)
- `totalSpendUsd` (number)

### `llmkit_cost_query` (~72 tokens)

Query cost breakdown grouped by provider, model, session, or day

Input parameters:

- `days` (number): Days to look back (default 30)
- `groupBy` (string, required): How to group results
- `model` (string): Filter by model
- `provider` (string): Filter by provider

Output parameters:

- `breakdown` (array)
- `days` (number)
- `groupBy` (string)

### `llmkit_list_keys` (~21 tokens)

List all API keys with status and creation date

Output parameters:

- `keys` (array)

### `llmkit_budget_status` (~34 tokens)

Check budget limits and remaining balance

Input parameters:

- `budgetId` (string): Specific budget ID, or omit for all

Output parameters:

- `budgets` (array)

### `llmkit_health` (~17 tokens)

Check proxy health and response time

Output parameters:

- `responseTimeMs` (number)
- `status` (string)

### `llmkit_session_summary` (~49 tokens)

Get recent proxy sessions with cost, duration, and models used

Input parameters:

- `limit` (number): Number of sessions (default 10)
- `sessionId` (string): Specific session ID

Output parameters:

- `sessions` (array)

### `llmkit_local_session` (~32 tokens)

Current session cost across all detected AI coding tools (Claude Code, Cline). No API key needed.

Output parameters:

- `sessions` (array)
- `sourceCount` (number)
- `totalCostUsd` (number)

### `llmkit_local_projects` (~30 tokens)

Cumulative cost across all projects and sessions from all detected AI coding tools, ranked by spend.

Output parameters:

- `projects` (array)
- `totalCostUsd` (number)

### `llmkit_local_cache` (~28 tokens)

Cache savings analysis across all detected AI coding tools. Shows how much prompt caching saved.

Output parameters:

- `savings` (array)
- `totalSavedUsd` (number)

### `llmkit_local_forecast` (~28 tokens)

Monthly cost projection based on local AI tool usage. Compares to Max subscription.

Output parameters:

- `dailyAverageUsd` (number)
- `maxSubscriptionSavingsUsd` (number)
- `projectedMonthlyUsd` (number)
- `totalSessions` (number)
- `totalTrackedUsd` (number)

### `llmkit_local_agents` (~29 tokens)

Subagent cost attribution for the current Claude Code session. Shows which agents cost the most.

Output parameters:

- `agentCount` (number)
- `byType` (array)
- `mainConversationCostUsd` (number)
- `sessionId` (string)
- `subagentsTotalCostUsd` (number)
- `totalCostUsd` (number)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/smigolsmigol-llmkit/f3d1-llmkit-mcp-server#diagnostics

## Score history

- 2026-08-03: 64
- 2026-08-02: 64
- 2026-08-01: 39
- 2026-07-31: 24
- 2026-07-30: 50
- 2026-07-28: 24
- 2026-07-27: 50

## Links

- npm package: https://www.npmjs.com/package/@f3d1/llmkit-mcp-server
- Socket report: https://socket.dev/npm/package/@f3d1/llmkit-mcp-server
- Repository: https://github.com/smigolsmigol/llmkit
- Changelog RSS feed: https://verifymcp.io/servers/smigolsmigol-llmkit/f3d1-llmkit-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/smigolsmigol-llmkit/f3d1-llmkit-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/smigolsmigol-llmkit/f3d1-llmkit-mcp-server