# The Neural Net

> Sourced register of open-weight AI model releases and AI news. Every field cites its source.

- name: com.theneuralnet/model-register
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 73/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.theneuralnet%2Fmodel-register
- tools: https://api.protogrid.dev/v1/servers/com.theneuralnet%2Fmodel-register/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "model-register": {
      "type": "http",
      "url": "https://theneuralnet.com/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-2d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 73/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: register_stats (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_model (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); recent_releases (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 747 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 2 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 747 tokens to load them all
- tool set hash: f7e800e02655993067d2f4c4a0e9d78f
- tools last changed: 2026-10-20T10:21:34.581Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.theneuralnet/model-register.svg)](https://protogrid.dev/servers/com.theneuralnet/model-register)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-20 `search_models` changed (inputSchema)

Full history: https://api.protogrid.dev/v1/servers/com.theneuralnet%2Fmodel-register/changes

## Remotes

- https://theneuralnet.com/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (6)

- `get_model`: 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.
- `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.
- `recent_releases`: 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'.
- `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.
- `search_models`: 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.
- `search_news`: 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.