MCP Radar
Serveur MCP

AI Compute Radar

dev.aicomputeradar/ai-compute-radar
IA et agents Cloud et infrastructure Données et analytique Public et accessible MCP 2025-11-25

Ce que fait ce MCP

Evaluates which tracked AI models fit specific GPUs or Macs and provides model trends, GPU rental prices, and weekly recommendations.

Capacités

Outils

5 outils
find_fit
Find models that fit a machine
Which tracked models run on a given GPU or Mac: measured GGUF weights + computed context cache + runtime overhead versus usable memory. Returns the best recommendation and every verdict (EXCELLENT/GOOD/TIGHT/OFFLOAD_REQUIRED/NOT_RECOMMENDED/UNKNOWN) with plain-language reasons. Get hardware ids from list_hardware.
Schéma d’entrée 
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['hardware'], 'properties': {'kv': {'enum': ['f16', 'q8_0', 'q4_0'], 'type': 'string', 'description': 'KV-cache quantization (default f16).'}, 'model': {'type': 'string', 'description': 'Restrict to one model slug.'}, 'context': {'type': 'integer', 'maximum': 1048576, 'minimum': 512, 'description': 'Context length in tokens (default 8192).'}, 'hardware': {'type': 'string', 'description': 'Hardware id or page slug, e.g. rtx-4090, mac-studio-m3-ultra-96gb.'}}}
gpu_prices
GPU rental prices
Median verified on-demand rental price per GPU class on Vast.ai (USD per hour), with min/p75 and offer counts, the collection timestamp, and per class the Rent Index: this week's median against last week and against the first week collected, a trend word, and the days excluded as marketplace glitches, plus RunPod's lowest posted on-demand price per class (a list price, not a median) and Clore.ai's median for the same class (a second marketplace, never blended). The index describes what prices did; it never forecasts.
Schéma d’entrée 
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {}}
list_hardware
List hardware profiles
Curated GPU and Mac profiles the fit engine knows — ids, memory, usable memory after margins, bandwidth. Use an id with find_fit.
Schéma d’entrée 
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {}}
trending_models
Trending models
Tracked AI models ranked by Heat Score (0–100, weighted percentiles of measured Hugging Face/OpenRouter signals) with the raw signals, local-run facts (GGUF size, quantization) and links. Models still collecting a week of history have heat=null and rank after scored ones.
Schéma d’entrée 
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'slug': {'type': 'string', 'description': 'Return a single model by slug.'}, 'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1, 'description': 'How many models to return (default 12).'}}}
weekly_pick
Pick of the week
The current pick of the week: one tracked model chosen by a published rule (largest counted Heat Score rise among models that run comfortably on a consumer card of up to 24 GB), with the numbers frozen at selection time, a device-by-device fit ladder and the written report including its caveats. Pass week (e.g. 2026-w37) for a past issue. issue is null until the first issue is published.
Schéma d’entrée 
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'week': {'type': 'string', 'pattern': '^\\d{4}-w\\d{2}$', 'description': 'ISO week label of a past issue, e.g. 2026-w37 (default: the current issue).'}}}
Historique

Modifications récentes des outils

Modifié
gpu_prices
25 September 2026 02:50
Modifié
gpu_prices
23 September 2026 02:41
Ajouté
weekly_pick
19 September 2026 02:40
Ajouté
list_hardware
19 September 2026 02:40
Ajouté
gpu_prices
19 September 2026 02:40
Ajouté
find_fit
19 September 2026 02:40
Ajouté
trending_models
19 September 2026 02:40
Découvrir

Serveurs MCP similaires

Algenta MCP Server

io.github.thyn-ai/algenta

Provides governed data onboarding, connector browsing, deterministic simulations, agent-run lifecycles, capability routing, deplo…

Replicate

io.github.pipeworx-io/replicate

Provides access to Replicate models, versions, collections, hardware, predictions, and deployments for running and managing hoste…

Scalix Cloud

world.scalix/cloud

Provides managed databases, SQL tools, container builds, persistent Linux machines, domains, scheduled functions, storage, and pr…

RationalBloks

io.github.rationalbloks/rationalbloks-mcp

Creates, deploys, manages, and searches schema-based REST API projects and Neo4j knowledge graphs across staging and production e…

RationalBloks

com.rationalbloks/mcp

Creates, deploys, manages, and queries REST API and Neo4j graph projects from JSON schemas, including graph data modeling, versio…

Huggingface

io.github.pipeworx-io/huggingface

Provides access to Hugging Face model, dataset, and Space metadata, alongside broader structured research and data-routing tools.

Ai Model Experiments

io.github.pipeworx-io/ai-model-experiments

Runs prompts across multiple AI models and compares their outputs, costs, latency, token usage, and errors.

Cloudflare Radar

io.github.pipeworx-io/cloudflare-radar

Provides Cloudflare Radar internet observatory data on DDoS attacks, BGP leaks, domain popularity, internet quality, and traffic …