# Robot Resources Router (npm · @robot-resources/router-mcp)

Intelligent LLM routing proxy — 60-90% cost savings by auto-selecting the cheapest model

- Trust score: 60/100 (medium)
- Change this week: +20
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

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

## Channel facts

- Registry: `npm`
- Package: `@robot-resources/router-mcp`
- Version: `0.1.2`
- 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 2026-08-03.

- **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**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 118 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 436 tokens (~109/item across 4 items; 4 tools + 0 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.

**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 robot-resources-router -- npx -y @robot-resources/router-mcp
```

### Codex

```bash
codex mcp add robot-resources-router -- npx -y @robot-resources/router-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add robot-resources-router --command npx --arg -y --arg @robot-resources/router-mcp
```

### Hermes

```yaml
mcp_servers:
  robot-resources-router:
    command: "npx"
    args: ["-y", "@robot-resources/router-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "robot-resources-router": {
      "command": "npx",
      "args": [
        "-y",
        "@robot-resources/router-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.

### 2026-08-02 (score 60, +44)

- [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 improvement] Schema quality: unverified → excellent
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 16, −5)

- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified

### 2026-07-31 (score 21, −19)

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

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

First indexed and scored.

## MCP tools (4)

### `router_get_stats` (~109 tokens)

Router Get Stats

Get routing cost savings statistics from Robot Resources Router. Shows how much money has been saved by intelligent model routing, with breakdowns by task type and provider.

Input parameters:

- `period` (string): Time period for stats: weekly (7 days), monthly (30 days), or all time
- `provider` (string): Filter by provider (openai, anthropic, google)
- `task_type` (string): Filter by task type (coding, reasoning, analysis, simple_qa, creative, general)

Output parameters:

- `average_savings_per_request` (number)
- `breakdown_by_provider` (object)
- `breakdown_by_task_type` (object)
- `period` (string)
- `total_cost_actual` (number)
- `total_cost_baseline` (number)
- `total_cost_saved` (number)
- `total_requests` (number)

### `router_compare_models` (~110 tokens)

Router Compare Models

Compare available LLM models for a specific task type. Returns all models ranked by cost with capability scores, savings vs baseline, and a recommendation for the cheapest model that meets the capability threshold.

Input parameters:

- `provider` (string): Filter by provider (openai, anthropic, google)
- `task_type` (string, required): Task type to compare models for
- `threshold` (number): Minimum capability score (0.0–1.0). Models below this are still shown but marked as not meeting threshold

Output parameters:

- `baseline_model` (string)
- `capable_models` (number)
- `models` (array)
- `recommended`
- `task_type` (string)
- `threshold` (number)
- `total_models` (number)

### `router_get_config` (~48 tokens)

Router Get Config

Get the current Router routing configuration. Returns effective config (env-var defaults merged with any runtime overrides). Shows provider_scope, capability_threshold, baseline_model, log_level, and which fields are overridden.

Output parameters:

- `baseline_model` (string)
- `capability_threshold` (number)
- `log_level` (string)
- `overrides` (array)
- `provider_scope` (string)

### `router_set_config` (~169 tokens)

Router Set Config

Update Router routing configuration at runtime. Only provide fields you want to change — other fields keep their current values. Send null for a field to reset it to the env-var default. Overrides are in-memory only and cleared on proxy restart.

Input parameters:

- `baseline_model`: Baseline model for savings comparison (e.g., gpt-4o). Must exist in models database. Send null to reset to default.
- `capability_threshold`: Minimum capability score for model selection (0.0–1.0). Lower = cheaper but less capable. Send null to reset to default.
- `log_level`: Logging verbosity level. Send null to reset to default.
- `provider_scope`: Provider scope for routing. "all" uses all providers, or restrict to one. Send null to reset to default.

Output parameters:

- `baseline_model` (string)
- `capability_threshold` (number)
- `log_level` (string)
- `overrides` (array)
- `provider_scope` (string)

## Diagnostics

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

## Score history

- 2026-08-03: 60
- 2026-08-02: 60
- 2026-08-01: 16
- 2026-07-31: 21
- 2026-07-30: 40
- 2026-07-28: 40
- 2026-07-27: 40

## Links

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