AI Stupid Level

io.github.StudioPlatformsPublished by GitHub account StudioPlatformsv0.1.1Updated Oct 26, 2026

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

VerifiedSTDIODesktop onlyDeveloper ToolsData & AnalyticsAI & ML

Overview

AI-generated overview

Reads AI Stupid Level's LLM leaderboard, drift, incidents and provider status, and can preview or send prompts through its Smart Router.

What you can do
  • Read leaderboards and model details: rankings by combined, coding, reasoning or tool-use score, per-model info, score history and drift status
  • Check reliability: recent provider and per-model incidents, provider API health probes, and ASL's global index
  • Get recommendations: current picks such as best for coding, most reliable, fastest, best value or avoid now
  • Preview routing: see which model the Smart Router would pick for a prompt, with score, estimated cost, reason and fallback chain
  • Send prompts through the router and check usage: get the answer, model, latency and tokens, plus monthly router usage and remaining data requests
  • Use a choose_model prompt that walks the assistant through…
When to use it
Useful when you want model-choice advice grounded in benchmark data: comparing models for coding or reasoning, checking whether a model has degraded recently, or seeing which model a router would choose before committing a request.
Requirements
Runs locally over stdio via npx, needing Node.js 18 or later. A data key in ASL_DATA_KEY is needed for leaderboard, history, drift, incidents, provider status, recommendations and the global index; a router key in ASL_ROUTER_KEY is needed for preview_route, ask_router and router usage, and the router account needs at least one provider key. Keys are optional individually; tools without a key return a message saying which key is needed.
Before you install
Two secrets are requested: ASL_DATA_KEY and ASL_ROUTER_KEY. ask_router is not read-only: it sends your prompt through the router, which calls the model with your own provider key, so the provider bills you and the request counts against your plan; use sandbox mode to get mock answers at no cost. Free data keys are limited to 10 requests a day and 1 a minute, and a request refused for quota still counts. Republished data requires attribution to aistupidlevel.info.

Installation

In SourceWeft

  1. Open AI Stupid Level in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@aistupidlevel/mcp

An MCP server for AI Stupid Level (ASL). It lets Claude, Cursor, VS Code or any other MCP client read ASL's LLM leaderboard, score history, drift status, incidents and provider status. With a router key it can also ask the ASL Smart Router which model it would pick for a prompt, or send the prompt through the router.

Ask your assistant things like:

  • "Which model is best for coding right now, according to AI Stupid Level?"
  • "Has Claude Opus 5.5 got worse this week?"
  • "Were there any provider incidents in the last few days?"
  • "Which model would the Smart Router pick for this prompt, and why?"

It runs locally over stdio and needs Node.js 18 or later.

Keys

The tools use two different keys, and you only need the one for the tools you want.

KeyUsed byWhere to get it
ASL_DATA_KEY (asl_live_…)leaderboard, model, history, drift, incidents, providers, recommendations, global indexhttps://aistupidlevel.info/account/data-keys (free tier available)
ASL_ROUTER_KEY (aism_…)preview_route, ask_router, router usagehttps://aistupidlevel.info/router/keys, plus at least one provider key in your account

A tool whose key is missing does not fail the server. It answers with a message that says which key it needs and where to create it.

ASL_API_KEY is also accepted: it is used as the data key if it starts with asl_, and as the router key if it starts with aism_.

Free-tier limits

A free Data API key allows 10 requests a day and 1 a minute. Paid plans allow 10,000 a day or more (pricing). The free tier is meant for trying the API, so the server is careful with it:

  • Every answer is cached in memory for 15 minutes (ASL_CACHE_TTL). Asking the same question again, or for another vendor or a shorter list from the same leaderboard, makes no request, and model names are looked up in the cached leaderboard.
  • One tool call makes at most one Data API request. The exception is a model given by name before any leaderboard has been fetched, which takes one extra request to look up the model ids.
  • Once the daily quota is used up, the server stops sending requests until 00:00 UTC. A request refused for quota still counts against it.
  • If a fresh answer cannot be fetched, the server returns the last cached answer (up to 24 hours old) and says how old it is.
  • Every answer ends with the number of requests left today.

On a free key, calling several different data tools within a minute hits the per-minute limit. The tool then says when to try again. If the wait is 15 seconds or less (ASL_MAX_WAIT), the server waits and retries once by itself.

The newest-run view (period: "latest") needs a paid key. Free keys read the 24-hour, 7-day and 30-day views.

preview_route and get_usage are not counted against your Smart Router plan. ask_router is a real routed request: the router calls the model with your own provider key, so the provider bills you and the request counts against your plan. Pass sandbox: true, or set ASL_SANDBOX=true, to get mock answers from the real routing at no cost.

Install

The package runs with npx, so there is nothing to install first. Put your keys in place of the placeholders, and leave out any key you do not have.

Claude Code

sh
claude mcp add aistupidlevel -e ASL_DATA_KEY=asl_live_... -e ASL_ROUTER_KEY=aism_... -- npx -y @aistupidlevel/mcp

Add -s user to make it available in every project.

Claude Desktop

Settings → Developer → Edit Config, then add the server to claude_desktop_config.json:

json
{  "mcpServers": {    "aistupidlevel": {      "command": "npx",      "args": ["-y", "@aistupidlevel/mcp"],      "env": {        "ASL_DATA_KEY": "asl_live_...",        "ASL_ROUTER_KEY": "aism_..."      }    }  }}

Restart Claude Desktop afterwards.

Cursor

Add the following to ~/.cursor/mcp.json (for all projects) or .cursor/mcp.json (for one project):

json
{  "mcpServers": {    "aistupidlevel": {      "command": "npx",      "args": ["-y", "@aistupidlevel/mcp"],      "env": {        "ASL_DATA_KEY": "asl_live_...",        "ASL_ROUTER_KEY": "aism_..."      }    }  }}

VS Code

Add the following to .vscode/mcp.json (or to your user configuration with MCP: Open User Configuration). VS Code prompts for the keys and stores them securely:

json
{  "inputs": [    { "type": "promptString", "id": "asl-data-key", "description": "AI Stupid Level Data API key (asl_live_...)", "password": true },    { "type": "promptString", "id": "asl-router-key", "description": "AI Stupid Level router key (aism_...)", "password": true }  ],  "servers": {    "aistupidlevel": {      "type": "stdio",      "command": "npx",      "args": ["-y", "@aistupidlevel/mcp"],      "env": {        "ASL_DATA_KEY": "${input:asl-data-key}",        "ASL_ROUTER_KEY": "${input:asl-router-key}"      }    }  }}

Other clients

Any client that can start a stdio server can run it: the command is npx -y @aistupidlevel/mcp, and the keys go in the environment variables listed under Configuration.

Docker

The image builds the server from source. From the repository root:

sh
docker build -f packages/mcp/Dockerfile -t aistupidlevel-mcp .docker run -i --rm -e ASL_DATA_KEY=asl_live_... -e ASL_ROUTER_KEY=aism_... aistupidlevel-mcp

Tools

All tools except ask_router are read-only.

ToolKeyWhat it returns
get_leaderboarddataTracked models ranked by combined, coding, reasoning or tool-use score, or by score per list-price dollar. Each row has the score, trend, status and stability, and the model ids the other tools take. Filter by vendor; choose the view (24h, 7d, 1m, or latest on a paid key).
get_modeldataOne model's details: vendor, version, notes, tool-calling support and days tracked.
get_model_historydataOne model's score for each run in the window, with a summary and the per-axis results of the newest run.
get_drift_statusdataOne model's drift signature: regime, current score against its baseline, the change-point detector for each suite, the last significant change, and which axes moved.
get_incidentsdataRecent incidents (provider-wide and per model) with severity, the models affected, when each was detected and when it was resolved.
get_provider_statusdataEach provider's API status from ASL's health probes, with the probe's response time and the last error.
get_recommendationsdataASL's current picks (best for coding, most reliable, fastest, best value, poor value, avoid now), each with its reason and the evidence behind it.
get_global_indexdataASL's global index across the tracked models, now and over the last 24 hours.
preview_routerouterThe model the Smart Router would pick for a prompt, its score and estimated cost, the reason, and the fallback chain. Nothing is called or counted.
ask_routerrouterSends a prompt through the Smart Router and returns the answer, the model and provider that answered, why it was chosen, the latency and the tokens used. Set sandbox: true for a mock answer at no cost.
get_usageeitherThis month's router usage and budget, and the Data API requests left today.

Models can be given by numeric id, by name (claude-opus-5-5) or by display name (Claude Opus 5.5).

preview_route and ask_router take a routing mode (auto, auto-best, auto-coding, auto-reasoning, auto-tooling, auto-task, auto-value, auto-value-coding, auto-value-reasoning, auto-value-tooling, auto-fastest-quality, auto-consistent, auto-fastest, auto-cheapest), or pin_model to name a model directly. The router documentation explains each mode.

The server also provides one prompt, choose_model, which walks the assistant through choosing a model for a task you describe.

Answers from the Data API end with a source line. The data is licensed with attribution required: cite aistupidlevel.info when you republish it.

Configuration

VariableDefaultMeaning
ASL_DATA_KEYnoneData API key (asl_live_…)
ASL_ROUTER_KEYnoneSmart Router key (aism_…)
ASL_SANDBOXfalsetrue puts every Smart Router call in sandbox mode: real routing, mock answer, nothing spent or counted
ASL_CACHE_TTL900Seconds a Data API answer is reused
ASL_MAX_WAIT15When the per-minute limit asks for a wait this short (seconds) or shorter, wait and retry once. 0 turns this off
ASL_TIMEOUT_MS300000Timeout for a Smart Router request

Keys are never logged. The server writes its diagnostics to stderr, because stdout carries the MCP protocol.

Use as a library

ts
import { createServer } from '@aistupidlevel/mcp';import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
const server = createServer({ dataKey: process.env.ASL_DATA_KEY, cacheTtlSeconds: 600 });await server.connect(new StdioServerTransport());

createServer accepts the same settings as the environment variables, plus a custom fetch.

Development

sh
npm ci && npm run build && npm test

The unit tests start the server in-process, connect an MCP client to it over an in-memory transport, and replay real API responses from test/fixtures. The live tests are skipped unless keys are set:

sh
ASL_ROUTER_KEY=aism_... npm test    # Smart Router, sandbox only: nothing is spent or countedASL_DATA_KEY=asl_live_... npm test  # Data API: one request

Links

MIT licence.

Source: packages/mcp/README.md at commit b58a173

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

2
  1. v0.1.1LatestOct 20, 2026
  2. v0.1.0Oct 20, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts