The Neural Net
Sourced register of open-weight AI model releases and AI news. Every field cites its source.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"model-register": {
"url": "https://theneuralnet.com/api/mcp"
}
}
}远程端点
https://theneuralnet.com/api/mcpstreamable-http它能做什么
工具清单
工具（6）
🟢search_models(organisation, license, task, min_parameters, max_parameters, ...)
Search the model register: open-weight AI model releases with exact parameter counts, architectural context length, licence and release date. Use this to answer questions about which models exist, how big they are, what they are licensed under, or what shipped recently.
输入模式
{
"type": "object",
"properties": {
"organisation": {
"type": "string",
"description": "e.g. qwen, deepseek-ai, meta-llama, google"
},
"license": {
"type": "string",
"description": "e.g. apache-2.0, mit"
},
"task": {
"type": "string",
"description": "e.g. text-generation, image-text-to-text, mask-generation"
},
"min_parameters": {
"type": "number",
"description": "Minimum parameter count, e.g. 7000000000"
},
"max_parameters": {
"type": "number"
},
"min_context": {
"type": "number",
"description": "Minimum architectural context length in tokens"
},
"tool_calling": {
"type": "boolean",
"description": "Only models whose chat template shows tool-calling support"
},
"reasoning": {
"type": "boolean",
"description": "Only models whose chat template shows reasoning/thinking support"
},
"image_input": {
"type": "boolean",
"description": "Only models that accept image input"
},
"released_after": {
"type": "string",
"description": "ISO date, e.g. 2026-01-01"
},
"query": {
"type": "string",
"description": "Substring match on the model id"
},
"include_derivatives": {
"type": "boolean",
"description": "Include quantisations and conversions of other releases (GGUF, MLX, AWQ and similar). Default false."
},
"limit": {
"type": "number",
"description": "Default 25, max 100"
}
}
}🟢get_model(id)
Get the full record for one model, including every field and the endpoint each field was sourced from. Use when you need provenance or complete detail.
输入模式
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Repo id, e.g. \"Qwen/Qwen3.8-27B\""
}
},
"required": [
"id"
]
}⚪recent_releases(days, limit)
Models first recorded in the register within the last N days. Use to answer 'what shipped recently' or 'what is new in open-weight models'.
输入模式
{
"type": "object",
"properties": {
"days": {
"type": "number",
"description": "Look-back window, default 30"
},
"limit": {
"type": "number",
"description": "Default 25"
}
}
}⚪register_stats
Summary of what the register covers: how many models, field coverage, organisations tracked, and the inclusion rule. Use to judge whether the register can answer a question before querying it.
输入模式
{
"type": "object",
"properties": {}
}🟢search_news(query, topic, limit)
Search stories published by The Neural Net. Each story is written from a primary source and links to it. Use for narrative context on a release rather than raw model facts.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Substring match on headline and summary"
},
"topic": {
"type": "string",
"description": "e.g. models, products, infrastructure, research, policy, safety"
},
"limit": {
"type": "number",
"description": "Default 10"
}
}
}🟡get_wire
Everything The Neural Net harvested in the last day that it did not write up, grouped by source and linked to the original. Use for a broad view of current activity.
输入模式
{
"type": "object",
"properties": {}
}社区
证据