io.github.BlackFoil/claude-token-saver-mcp
NPM · CLAUDE-TOKEN-SAVER-MCP · SCANNED SEP 20
MCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens
Available components
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 Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 36 of 109 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 172 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability76
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 962 tokens (~87/item across 11 items; 11 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
- Stability observed for 27 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
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 11 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
How do I install the io.github.BlackFoil/claude-token-saver-mcp server?
io.github.BlackFoil/claude-token-saver-mcp runs locally as an npm package, launched with npx -y claude-token-saver-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 · claude-token-saver-mcp
claude mcp add blackfoil-claude-token-saver-mcp -- npx -y claude-token-saver-mcp
{
"mcpServers": {
"blackfoil-claude-token-saver-mcp": {
"command": "npx",
"args": [
"-y",
"claude-token-saver-mcp"
]
}
}
} {
"servers": {
"blackfoil-claude-token-saver-mcp": {
"command": "npx",
"args": [
"-y",
"claude-token-saver-mcp"
]
}
}
} codex mcp add blackfoil-claude-token-saver-mcp -- npx -y claude-token-saver-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"blackfoil-claude-token-saver-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"claude-token-saver-mcp"
],
"enabled": true
}
}
} openclaw mcp add blackfoil-claude-token-saver-mcp --command npx --arg -y --arg claude-token-saver-mcp
mcp_servers:
blackfoil-claude-token-saver-mcp:
command: "npx"
args: ["-y", "claude-token-saver-mcp"] {
"McpServers": {
"blackfoil-claude-token-saver-mcp": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"claude-token-saver-mcp"
]
}
}
} assistant mcp add blackfoil-claude-token-saver-mcp -t stdio -c npx -a -y claude-token-saver-mcp
{
"mcpServers": {
"blackfoil-claude-token-saver-mcp": {
"command": "npx",
"args": [
"-y",
"claude-token-saver-mcp"
]
}
}
} 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.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 −3
- Stability: pass → 0.80 functional
- 16 Sept 26 +1
- Stability: 0.97 → pass security
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Sept 26 −4
- Stability: pass → 0.77 functional
- 8 Sept 26 +1
- Stability: 0.97 → pass security
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 20 Sept 2026 · Analysed npm/claude-token-saver-mcp@0.3.2
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 →
Dependencies 109 packages
| Packages resolved | 109 |
|---|---|
| Stale | 36 |
| 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 →
auto_setup ~136
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 |
No output schema declared.
No examples provided.
batch_offload ~70
Submit multiple coding tasks as a batch to the local LLM. Tasks are processed sequentially or in parallel. Supports partial failure.
| Name | Type | Req | Description |
|---|---|---|---|
| sequential | boolean | – | Process tasks sequentially, passing previous result as context (default: false) |
| tasks | array | yes | Array of tasks (1-10) |
No output schema declared.
No examples provided.
compress_context ~132
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.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | 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). |
No output schema declared.
No examples provided.
configure_model_selector ~120
View or modify model selector settings at runtime. Manage blocked models, license filters, and custom model recommendations.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | 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 | yes | Which setting to manage |
| values | array | – | Values for set/add/remove (for blocked_models and license_filter) |
No output schema declared.
No examples provided.
cost_dashboard ~17
View cumulative cost savings and model usage statistics.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_metrics ~48
Get server metrics in Prometheus text format or JSON. Includes request counts, latency, queue stats, cost savings, and health status.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | Output format (default: json) |
No output schema declared.
No examples provided.
list_loaded_models ~33
List all models currently loaded in VRAM with usage details. Shows VRAM usage, expiry time, and available slots.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
offload_work ~162
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | yes | The task to perform (required, max 50000 chars) |
No output schema declared.
No examples provided.
preload_model ~93
Preload a model into VRAM for warm inference. Sends an empty chat request with keep_alive to keep the model loaded during the session.
| Name | Type | Req | Description |
|---|---|---|---|
| keep_alive | string | – | Duration to keep the model loaded (optional, default: "-1" = permanent). Examples: "5m", "1h", "-1" |
| model | string | yes | The model name to preload (must be already installed via pull_model) |
No output schema declared.
No examples provided.
pull_model ~64
Download a model from the Ollama registry to local storage. Use this to install recommended models before preloading them into VRAM.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | yes | Model name to pull (e.g. "qwen3:14b", "devstral:24b") |
No output schema declared.
No examples provided.
recommend_model ~87
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.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | yes | Task category: coding, coding-agent, japanese-text, japanese-coding, translation, summarization, general |
| prefer_quality | boolean | – | Prefer quality (true) or speed (false). Default: false |
No output schema declared.
No examples provided.
What is the io.github.BlackFoil/claude-token-saver-mcp server?
io.github.BlackFoil/claude-token-saver-mcp is listed in the public MCP registry as io.github.BlackFoil/claude-token-saver-mcp. MCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens. This page covers its npm package (claude-token-saver-mcp).
Is the io.github.BlackFoil/claude-token-saver-mcp server safe to use?
io.github.BlackFoil/claude-token-saver-mcp scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 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 io.github.BlackFoil/claude-token-saver-mcp server expose?
io.github.BlackFoil/claude-token-saver-mcp exposes 11 tools: offload_work, compress_context, cost_dashboard, batch_offload, get_metrics, and 6 more. Their descriptions and schemas cost roughly 962 tokens of context every time the server is loaded.
Is the io.github.BlackFoil/claude-token-saver-mcp server still maintained?
io.github.BlackFoil/claude-token-saver-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 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 io.github.BlackFoil/claude-token-saver-mcp server under?
io.github.BlackFoil/claude-token-saver-mcp 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.