# io.github.BlackFoil/claude-token-saver-mcp (npm · claude-token-saver-mcp)

MCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens

- Trust score: 68/100 (medium)
- Change this week: +22
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `claude-token-saver-mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/blackfoil-claude-token-saver-mcp/claude-token-saver-mcp.md), [page](https://verifymcp.io/servers/blackfoil-claude-token-saver-mcp/claude-token-saver-mcp)

## Channel facts

- Registry: `npm`
- Package: `claude-token-saver-mcp`
- Version: `0.3.2`
- 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 2026-08-04.

- **Supply Chain Security**: 83/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known medium-severity CVE affects hono 4.12.33, reached via @modelcontextprotocol/sdk > hono. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (108 of 112), 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 (Apache-2.0).
  - Actively maintained (last published 125 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 962 tokens (~87/item across 11 items; 11 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 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 blackfoil-claude-token-saver-mcp -- npx -y claude-token-saver-mcp
```

### Codex

```bash
codex mcp add blackfoil-claude-token-saver-mcp -- npx -y claude-token-saver-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "blackfoil-claude-token-saver-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "claude-token-saver-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add blackfoil-claude-token-saver-mcp --command npx --arg -y --arg claude-token-saver-mcp
```

### Hermes

```yaml
mcp_servers:
  blackfoil-claude-token-saver-mcp:
    command: "npx"
    args: ["-y", "claude-token-saver-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "blackfoil-claude-token-saver-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "claude-token-saver-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-04 (score 68, 0)

- [security regression] CVE-2026-69207 affects this package: medium
- [security regression] Known CVEs: partial → fail

### 2026-08-03 (score 68, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 64, +43)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: 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 improvement] License: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified
- [functional] Licence: Apache-2.0

### 2026-07-31 (score 21, −25)

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

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (11)

### `offload_work` (~162 tokens)

Offload coding/text tasks to a local LLM (Ollama) to save Claude API tokens. Use for code generation, refactoring, formatting, boilerplate, and other routine tasks.

Input parameters:

- `category` (string): Task category for automatic model selection (optional). Ignored if model is specified.
- `context` (string): Additional context such as file content or specifications (optional, max 100000 chars)
- `language` (string): Programming language (optional)
- `model` (string): Override the Ollama model to use (optional). Takes precedence over category-based selection.
- `output_format` (string): Output format (optional, default: code)
- `task` (string, required): The task to perform (required, max 50000 chars)

### `compress_context` (~132 tokens)

Compress/summarize large text content using a local LLM to reduce cloud token usage. Use for summarizing logs, large files, or verbose context before sending to Claude.

Input parameters:

- `content` (string, required): The content to compress/summarize (required, max 200000 chars)
- `focus` (string): What to focus on in the summary (optional, max 500 chars)
- `max_length` (number): Target max length of the summary in chars (optional, 100-10000, default: 2000)
- `model` (string): Override the Ollama model to use (optional).

### `cost_dashboard` (~17 tokens)

View cumulative cost savings and model usage statistics.

### `batch_offload` (~70 tokens)

Submit multiple coding tasks as a batch to the local LLM. Tasks are processed sequentially or in parallel. Supports partial failure.

Input parameters:

- `sequential` (boolean): Process tasks sequentially, passing previous result as context (default: false)
- `tasks` (array, required): Array of tasks (1-10)

### `get_metrics` (~48 tokens)

Get server metrics in Prometheus text format or JSON. Includes request counts, latency, queue stats, cost savings, and health status.

Input parameters:

- `format` (string): Output format (default: json)

### `recommend_model` (~87 tokens)

Recommend the best local LLM model for a given task category based on system specs and installed models. Returns prioritized list with installation status and license info.

Input parameters:

- `category` (string, required): Task category: coding, coding-agent, japanese-text, japanese-coding, translation, summarization, general
- `prefer_quality` (boolean): Prefer quality (true) or speed (false). Default: false

### `preload_model` (~93 tokens)

Preload a model into VRAM for warm inference. Sends an empty chat request with keep_alive to keep the model loaded during the session.

Input parameters:

- `keep_alive` (string): Duration to keep the model loaded (optional, default: "-1" = permanent). Examples: "5m", "1h", "-1"
- `model` (string, required): The model name to preload (must be already installed via pull_model)

### `list_loaded_models` (~33 tokens)

List all models currently loaded in VRAM with usage details. Shows VRAM usage, expiry time, and available slots.

### `pull_model` (~64 tokens)

Download a model from the Ollama registry to local storage. Use this to install recommended models before preloading them into VRAM.

Input parameters:

- `model` (string, required): Model name to pull (e.g. "qwen3:14b", "devstral:24b")

### `configure_model_selector` (~120 tokens)

View or modify model selector settings at runtime. Manage blocked models, license filters, and custom model recommendations.

Input parameters:

- `action` (string, required): Action to perform. "add"/"remove" for blocked_models/license_filter only.
- `custom_config` (object): Custom recommendations config for "set" action on custom_recommendations. Format: { category: { tier: [modelId, ...] } }
- `setting` (string, required): Which setting to manage
- `values` (array): Values for set/add/remove (for blocked_models and license_filter)

### `auto_setup` (~136 tokens)

Automate the full model setup flow: recommend the best model for a task category, download it if needed, and preload it into VRAM — all in one step.

Input parameters:

- `category` (string): Task category: coding, coding-agent, japanese-text, japanese-coding, translation, summarization, general. Default: "general"
- `prefer_quality` (boolean): Prefer quality (true) or speed (false). Default: false
- `skip_preload` (boolean): Skip preloading the model into VRAM. Default: false
- `skip_pull` (boolean): Skip downloading the model if not installed. Default: false

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/blackfoil-claude-token-saver-mcp/claude-token-saver-mcp#diagnostics

## Score history

- 2026-08-04: 68
- 2026-08-03: 68
- 2026-08-02: 64
- 2026-08-01: 21
- 2026-07-31: 21
- 2026-07-30: 46
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/claude-token-saver-mcp
- Socket report: https://socket.dev/npm/package/claude-token-saver-mcp
- Repository: https://github.com/BlackFoil/claude-token-saver-mcp
- Changelog RSS feed: https://verifymcp.io/servers/blackfoil-claude-token-saver-mcp/claude-token-saver-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/blackfoil-claude-token-saver-mcp/claude-token-saver-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/blackfoil-claude-token-saver-mcp/claude-token-saver-mcp