Sourced register of open-weight AI model releases and AI news. Every field cites its source.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
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.
Repo id, e.g. "Qwen/Qwen3.8-27B"
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
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.
| Argument | Type | Description |
|---|---|---|
| id* | string | Repo id, e.g. "Qwen/Qwen3.8-27B" |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "Repo id, e.g. \"Qwen/Qwen3.8-27B\""
}
}
}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.
No arguments.
{
"type": "object",
"properties": {}
}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'.
| Argument | Type | Description |
|---|---|---|
| days | number | Look-back window, default 30 |
| limit | number | Default 25 |
{
"type": "object",
"properties": {
"days": {
"type": "number",
"description": "Look-back window, default 30"
},
"limit": {
"type": "number",
"description": "Default 25"
}
}
}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.
No arguments.
{
"type": "object",
"properties": {}
}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.
| Argument | Type | Description |
|---|---|---|
| task | string | e.g. text-generation, image-text-to-text, mask-generation |
| limit | number | Default 25, max 100 |
| query | string | Substring match on the model id |
| license | string | e.g. apache-2.0, mit |
| reasoning | boolean | Only models whose chat template shows reasoning/thinking support |
| image_input | boolean | Only models that accept image input |
| min_context | number | Minimum architectural context length in tokens |
| organisation | string | e.g. qwen, deepseek-ai, meta-llama, google |
| tool_calling | boolean | Only models whose chat template shows tool-calling support |
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.
| Argument | Type | Description |
|---|---|---|
| limit | number | Default 10 |
| query | string | Substring match on headline and summary |
| topic | string | e.g. models, products, infrastructure, research, policy, safety |
{
"type": "object",
"properties": {
"limit": {
"type": "number",
"description": "Default 10"
},
"query": {
"type": "string",
"description": "Substring match on headline and summary"
},
"topic": {
"type": "string",
"description": "e.g. models, products, infrastructure, research, policy, safety"
}
}
}| max_parameters |
| number |
| min_parameters | number | Minimum parameter count, e.g. 7000000000 |
| released_after | string | ISO date, e.g. 2026-01-01 |
| include_derivatives | boolean | Include quantisations and conversions of other releases (GGUF, MLX, AWQ and similar). Default false. |
{
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "e.g. text-generation, image-text-to-text, mask-generation"
},
"limit": {
"type": "number",
"description": "Default 25, max 100"
},
"query": {
"type": "string",
"description": "Substring match on the model id"
},
"license": {
"type": "string",
"description": "e.g. apache-2.0, mit"
},
"reasoning": {
"type": "boolean",
"description": "Only models whose chat template shows reasoning/thinking support"
},
"image_input": {
"type": "boolean",
"description": "Only models that accept image input"
},
"min_context": {
"type": "number",
"description": "Minimum architectural context length in tokens"
},
"organisation": {
"type": "string",
"description": "e.g. qwen, deepseek-ai, meta-llama, google"
},
"tool_calling": {
"type": "boolean",
"description": "Only models whose chat template shows tool-calling support"
},
"max_parameters": {
"type": "number"
},
"min_parameters": {
"type": "number",
"description": "Minimum parameter count, e.g. 7000000000"
},
"released_after": {
"type": "string",
"description": "ISO date, e.g. 2026-01-01"
},
"include_derivatives": {
"type": "boolean",
"description": "Include quantisations and conversions of other releases (GGUF, MLX, AWQ and similar). Default false."
}
}
}