# AI Stupid Level (npm · @aistupidlevel/mcp)

LLM benchmark rankings, drift status, incidents and Smart Router previews from AI Stupid Level.

- Trust score: 73/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@aistupidlevel/mcp`: 73/100 (this document), [markdown](https://verifymcp.io/servers/studioplatforms-aistupidlevel/aistupidlevel-mcp.md), [page](https://verifymcp.io/servers/studioplatforms-aistupidlevel/aistupidlevel-mcp)

## Channel facts

- Registry: `npm`
- Package: `@aistupidlevel/mcp`
- Version: `0.1.1`
- 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 2026-11-05.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 4.6.5, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 30 of 93 dependencies flagged as unhealthy.
- **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 15 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 79/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1968 tokens (~178/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the AI Stupid Level MCP server?

AI Stupid Level runs locally as an npm package, launched with npx -y @aistupidlevel/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add studioplatforms-aistupidlevel -- npx -y @aistupidlevel/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "studioplatforms-aistupidlevel": {
      "command": "npx",
      "args": [
        "-y",
        "@aistupidlevel/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "studioplatforms-aistupidlevel": {
      "command": "npx",
      "args": [
        "-y",
        "@aistupidlevel/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add studioplatforms-aistupidlevel -- npx -y @aistupidlevel/mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add studioplatforms-aistupidlevel --command npx --arg -y --arg @aistupidlevel/mcp
```

### Hermes

```yaml
mcp_servers:
  studioplatforms-aistupidlevel:
    command: "npx"
    args: ["-y", "@aistupidlevel/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "studioplatforms-aistupidlevel": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@aistupidlevel/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add studioplatforms-aistupidlevel -t stdio -c npx -a -y @aistupidlevel/mcp
```

### Other

```json
{
  "mcpServers": {
    "studioplatforms-aistupidlevel": {
      "command": "npx",
      "args": [
        "-y",
        "@aistupidlevel/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.

### 2026-11-04 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 70, +4)

- [functional improvement] Stability: unverified → 0.30

### 2026-10-24 (score 66, −5)

- [security regression] CVE-2023-54404 affects this package: high
- [security regression] Known CVEs: pass → fail

### 2026-10-21 (score 71, +26)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 0.85

### 2026-10-20 (score 45)

First indexed and scored.

## MCP tools (11)

### `get_leaderboard` (~247 tokens)

LLM leaderboard

Ranking of the LLM APIs AI Stupid Level tracks (OpenAI, Anthropic, Google, DeepSeek, Kimi, GLM models) by benchmark score, 0-100. Use it to find the best model overall or for coding, reasoning or tool use, to compare models, and to get the model ids the other tools accept. Each row has the score, trend, status, stability and when it was last updated.

Input parameters:

- `limit` (integer): How many models to show (default 10).
- `period` (string): Score window: 24h, 7d or 1m (30-day) averages, or latest (the newest run). Omit it to use the key's default: 24h on a free Data API key, latest on a paid one. latest needs a paid key.
- `sort_by` (string): Which ranking: combined (default, all suites), coding, reasoning, tooling (tool use / agentic tasks), or price (score per list-price dollar).
- `vendor` (string): Only show models from this vendor: openai, anthropic, google, deepseek, kimi or glm.

### `get_model` (~105 tokens)

Model details

Details AI Stupid Level holds on one tracked LLM: vendor, version, notes on how it is called and priced, tool-calling support, how long it has been tracked, and its leaderboard row when one has been fetched.

Input parameters:

- `model` (string, required): The model: its numeric id, its name (for example claude-opus-5-5 or gpt-6-sol) or its display name. get_leaderboard lists the tracked models with their ids.

### `get_model_history` (~206 tokens)

Model score history

Score history of one LLM on AI Stupid Level: each benchmark run in the window with its score, plus the newest run's per-axis results (correctness, code quality, efficiency, …). Use it to see whether a model got better or worse over time.

Input parameters:

- `max_points` (integer): How many runs to list, newest first (default 30). The summary always covers every run.
- `model` (string, required): The model: its numeric id, its name (for example claude-opus-5-5 or gpt-6-sol) or its display name. get_leaderboard lists the tracked models with their ids.
- `period` (string): Score window: 24h, 7d or 1m (30-day) averages, or latest (the newest run). Omit it to use the key's default: 24h on a free Data API key, latest on a paid one. latest needs a paid key.

### `get_drift_status` (~134 tokens)

Model drift status

Whether an LLM's measured performance has shifted: AI Stupid Level's drift signature for one model, with its regime (stable, degrading, …), current score against its baseline, the change-point detector per benchmark suite, the last significant change and which axes moved. Use it to answer "has model X got worse?" or "is X being nerfed?".

Input parameters:

- `model` (string, required): The model: its numeric id, its name (for example claude-opus-5-5 or gpt-6-sol) or its display name. get_leaderboard lists the tracked models with their ids.

### `get_incidents` (~109 tokens)

Recent incidents

Recent incidents AI Stupid Level recorded: provider-wide degradations and model-level problems, with severity, the models affected, when each was detected and whether and when it was resolved.

Input parameters:

- `limit` (integer): How many incidents to show, newest first (default 10).
- `open_only` (boolean): Only incidents that are not resolved yet (default false).
- `provider` (string): Only incidents for this provider: openai, anthropic, google, deepseek, kimi or glm.

### `get_provider_status` (~71 tokens)

Provider status

Current status of each LLM provider's API as AI Stupid Level's health probes see it (OpenAI, Anthropic, Google, DeepSeek, Kimi, GLM): operational or not, probe response time, the last error and when it was checked. For past outages use get_incidents.

### `get_recommendations` (~157 tokens)

Model recommendations

AI Stupid Level's current picks: the best model for coding, the most reliable (steadiest score), the fastest, the best value (most points per measured dollar among near-top models), models that cost far more than an equally good alternative, and models to avoid right now. Each pick comes with the reason and the evidence it rests on. Use it for "which model should I use?".

Input parameters:

- `period` (string): Score window: 24h, 7d or 1m (30-day) averages, or latest (the newest run). Omit it to use the key's default: 24h on a free Data API key, latest on a paid one. latest needs a paid key.

### `get_global_index` (~60 tokens)

Global AI index

AI Stupid Level's global index: one 0-100 number for the tracked models together, now and over the last 24 hours, with its trend and how many models are performing well. Use it for "are AI models worse today?".

### `preview_route` (~289 tokens)

Preview Smart Router choice

Which model the AI Stupid Level Smart Router would send a prompt to, and why: the routing strategy, the chosen model and provider with its benchmark score and estimated cost, and the fallback chain. Nothing is sent to a model and nothing is counted. Needs a router key (ASL_ROUTER_KEY).

Input parameters:

- `mode` (string): Routing mode (default auto = the strategy saved in the account): auto-best (highest combined score), auto-coding, auto-reasoning, auto-tooling (top model on that benchmark), auto-task (reads the prom…
- `pin_model` (string): Pin a specific model id (for example gpt-6-sol) instead of a routing mode.
- `prompt` (string, required): The prompt to route (the decision can depend on it, for example with auto-task).
- `sandbox` (boolean): Sandbox: run the real routing as if the account had a key for every provider and return a mock answer. Nothing is called, spent or counted.
- `system` (string): An optional system message.

### `ask_router` (~336 tokens)

Ask via Smart Router

Send a prompt through the AI Stupid Level Smart Router and return the answer, together with which model answered, its provider, why the router chose it and the latency. The router calls the model with the provider keys saved in the user's ASL account, so a real call is billed by that provider and counts against the router plan; set sandbox: true for a free mock answer. Needs a router key (ASL_ROUTER_KEY).

Input parameters:

- `max_tokens` (integer): Upper bound on the answer length in tokens.
- `mode` (string): Routing mode (default auto = the strategy saved in the account): auto-best (highest combined score), auto-coding, auto-reasoning, auto-tooling (top model on that benchmark), auto-task (reads the prom…
- `pin_model` (string): Pin a specific model id (for example gpt-6-sol) instead of a routing mode.
- `prompt` (string, required): The user message to send.
- `reasoning_effort` (string): Reasoning effort for models that support it.
- `sandbox` (boolean): Sandbox: run the real routing as if the account had a key for every provider and return a mock answer. Nothing is called, spent or counted.
- `system` (string): An optional system message.

### `get_usage` (~61 tokens)

ASL usage and limits

This month's Smart Router usage for the configured router key (requests used and left, prepaid credits, the key's budget), and the Data API requests left today for the configured data key. Use it when a tool reports a limit, or to check the keys work.

## Diagnostics

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

## Score history

- 2026-11-05: 73
- 2026-11-04: 73
- 2026-11-03: 72
- 2026-11-02: 72
- 2026-11-01: 71
- 2026-10-31: 71
- 2026-10-30: 70
- 2026-10-29: 70
- 2026-10-28: 66
- 2026-10-27: 66
- 2026-10-26: 66
- 2026-10-25: 66
- 2026-10-24: 66
- 2026-10-23: 71
- 2026-10-22: 71
- 2026-10-21: 71
- 2026-10-20: 45

## Common questions

### What is the AI Stupid Level MCP server?

AI Stupid Level is an MCP server listed in the public MCP registry as io.github.StudioPlatforms/aistupidlevel. LLM benchmark rankings, drift status, incidents and Smart Router previews from AI Stupid Level. This page covers its npm package (@aistupidlevel/mcp).

### Is the AI Stupid Level MCP server safe to use?

AI Stupid Level scores 73 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 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 AI Stupid Level MCP server expose?

AI Stupid Level exposes 11 tools: get_leaderboard, get_model, get_model_history, get_drift_status, get_incidents, and 6 more. Their descriptions and schemas cost roughly 1,775 tokens of context every time the server is loaded.

### Is the AI Stupid Level MCP server still maintained?

AI Stupid Level is still listed as active in the MCP registry. We last reached this channel on 5 November 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 AI Stupid Level MCP server under?

AI Stupid Level declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@aistupidlevel/mcp
- Socket report: https://socket.dev/npm/package/@aistupidlevel/mcp
- Repository: https://github.com/StudioPlatforms/aistupidlevel-sdk
- Website: https://aistupidlevel.info/router/docs
- Changelog RSS feed: https://verifymcp.io/servers/studioplatforms-aistupidlevel/aistupidlevel-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/studioplatforms-aistupidlevel/aistupidlevel-mcp.json
- HTML version of this page: https://verifymcp.io/servers/studioplatforms-aistupidlevel/aistupidlevel-mcp