# io.github.Rckl88/clawbackai-mcp (npm · clawbackai-mcp)

LLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.

- Trust score: 60/100 (medium)
- Change this week: +20
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `clawbackai-mcp`: 60/100 (this document), [markdown](https://verifymcp.io/servers/rckl88-clawbackai-mcp/clawbackai-mcp.md), [page](https://verifymcp.io/servers/rckl88-clawbackai-mcp/clawbackai-mcp)

## Channel facts

- Registry: `npm`
- Package: `clawbackai-mcp`
- Version: `1.0.0`
- 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 2026-08-04.

- **Supply Chain Security**: 83/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known medium-severity CVE affects @hono/node-server 1.19.17, reached via @modelcontextprotocol/sdk > @hono/node-server. A fixed version is available.
  - 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**: 19/100
  - Repository check failed: the declared repository URL redirects; it must resolve directly.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 109 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 463 tokens (~57/item across 8 items; 8 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**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 84% 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 rckl88-clawbackai-mcp -- npx -y clawbackai-mcp
```

### Codex

```bash
codex mcp add rckl88-clawbackai-mcp -- npx -y clawbackai-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "rckl88-clawbackai-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "clawbackai-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add rckl88-clawbackai-mcp --command npx --arg -y --arg clawbackai-mcp
```

### Hermes

```yaml
mcp_servers:
  rckl88-clawbackai-mcp:
    command: "npx"
    args: ["-y", "clawbackai-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "rckl88-clawbackai-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "clawbackai-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 60, +5)

- [security regression] CVE-2026-69207 affects this package: medium
- [functional improvement] Stability: unverified → 0.30

### 2026-08-02 (score 55, +40)

- [security regression] GHSA-frvp-7c67-39w9 affects this package: medium
- [security regression] Known CVEs: unverified → fail
- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

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

- [functional improvement] Tool coverage: unverified → 100

### 2026-07-31 (score 0, −22)

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

### 2026-07-30 (score 22, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 40)

First indexed and scored.

## MCP tools (8)

### `start_audit` (~74 tokens)

Start a free Clawback audit. Registers your API key for traffic observation. Route 50+ calls through clawback.run/v1 to trigger the audit automatically.

Input parameters:

- `api_key` (string, required): Your provider API key (hashed for identification, never stored raw)
- `email` (string): Optional email for report delivery

### `get_audit_status` (~51 tokens)

Check audit progress. Returns calls logged, report URL when ready, routing recommendations, and next steps. Share the report URL with a human decision maker.

Input parameters:

- `api_key` (string, required): Your API key

### `activate_routing` (~49 tokens)

Activate smart routing after reviewing audit results. Only call after get_audit_status shows a completed report.

Input parameters:

- `api_key` (string, required): Your API key
- `strategy` (string): Routing strategy

### `optimize_llm_call` (~81 tokens)

Route a completion to the best model. Requires routing to be activated first via the audit flow.

Input parameters:

- `api_key` (string, required): Your provider API key
- `max_tokens` (integer)
- `messages` (array, required): OpenAI-format messages array
- `model` (string, required): The model you would normally use
- `temperature` (number)

### `get_frontier` (~37 tokens)

Get the efficient frontier — best quality per dollar by task type. No API key needed.

Input parameters:

- `task_type` (string): Task type

### `check_savings` (~35 tokens)

Check monthly and all-time routing value (price difference captured per routed call).

Input parameters:

- `api_key` (string, required): Your API key

### `get_model_recommendation` (~70 tokens)

Get the recommended model for a task type without making an API call. No key needed.

Input parameters:

- `max_cost_per_million` (number): Max cost per million tokens
- `min_quality` (number): Minimum quality score (0-100)
- `task_type` (string): Task type

### `set_agent_budget` (~66 tokens)

Set per-agent monthly budget. Requires routing to be active.

Input parameters:

- `action_on_exceed` (string)
- `agent_name` (string, required): Agent name
- `api_key` (string, required): Your API key
- `monthly_budget_usd` (number, required): Monthly budget in USD

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/rckl88-clawbackai-mcp/clawbackai-mcp#diagnostics

## Score history

- 2026-08-04: 60
- 2026-08-03: 55
- 2026-08-02: 55
- 2026-08-01: 15
- 2026-07-31: 0
- 2026-07-30: 22
- 2026-07-28: 40
- 2026-07-27: 40

## Links

- npm package: https://www.npmjs.com/package/clawbackai-mcp
- Socket report: https://socket.dev/npm/package/clawbackai-mcp
- Changelog RSS feed: https://verifymcp.io/servers/rckl88-clawbackai-mcp/clawbackai-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/rckl88-clawbackai-mcp/clawbackai-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/rckl88-clawbackai-mcp/clawbackai-mcp