SoftPerceptron
AI model/agent directory with pricing and comparisons, plus GPU VRAM fit and tokens/sec estimates.
使うべきか
品質と安全性
検出事項（1）
- LOWTool 'compare_ai_models' description lacks action verbcompare_ai_models 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"mcp": {
"url": "https://softperceptron.com/mcp"
}
}
}リモートエンドポイント
https://softperceptron.com/mcpstreamable-httpできること
ツール一覧
ツール（6）
🟢search_ai_models(query, kind, limit)
Search the SoftPerceptron directory of AI models, autonomous agents and token/credit products. Returns pricing, specs and provider for each match. Use this to answer questions like 'what AI models are available', 'cheapest model with a big context window', or 'which coding agents exist'.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Free-text match against name, tagline, provider and tags. Omit to list everything."
},
"kind": {
"type": "string",
"enum": [
"model",
"agent",
"token"
],
"description": "Restrict to one product kind."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Max results (default 10)."
}
}
}🟢get_ai_model(id)
Get full details for one directory entry by id or common alias (e.g. 'claude', 'gpt', 'gemini'). Returns pricing, specs, provider and links.
入力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Listing id or alias, e.g. 'anthropic-claude' or 'claude'."
}
},
"required": [
"id"
]
}⚪compare_ai_models(a, b)
Compare two directory entries side by side — pricing, context window, modality and what each is best for. Both must be the same kind (model vs model, agent vs agent).
入力スキーマ
{
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "First listing id or alias."
},
"b": {
"type": "string",
"description": "Second listing id or alias."
}
},
"required": [
"a",
"b"
]
}🟢can_i_run_model(model, gpu, quant, context)
Check whether a specific open-weight model fits on a specific GPU: VRAM required, whether it fits, how much headroom, which quantization to use, and an estimated decode speed in tokens/sec. Use for questions like 'can an RTX 4090 run Llama 70B'.
入力スキーマ
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Local model id or name, e.g. 'llama33-70b'. Call list_local_models to see options."
},
"gpu": {
"type": "string",
"description": "GPU id or name, e.g. 'rtx4090'. Call list_gpus to see options."
},
"quant": {
"type": "string",
"description": "Quantization id (default 'q4'), e.g. q4, q5, q8, fp16."
},
"context": {
"type": "integer",
"minimum": 512,
"maximum": 200000,
"description": "Context length in tokens (default 8192)."
}
},
"required": [
"model",
"gpu"
]
}🟢list_local_models
List the open-weight models supported by the VRAM/can-i-run calculator, with parameter counts and what each is good for.
入力スキーマ
{
"type": "object",
"properties": {}
}🟢list_gpus
List the GPUs supported by the VRAM calculator, with VRAM, memory bandwidth and power draw.
入力スキーマ
{
"type": "object",
"properties": {}
}コミュニティ
エビデンス