# Horse Truth Machine Intelligence (remote · horsetruth.com.au)

Derived Australian racehorse intelligence for AI agents, MCP clients, software and publishers.

- Trust score: 69/100 (medium)
- Change this week: +36
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-28

## Components

- remote · `horsetruth.com.au`: 69/100 (this document), [markdown](https://verifymcp.io/servers/au-com-horsetruth-machine-intelligence/api-v1-mcp.md), [page](https://verifymcp.io/servers/au-com-horsetruth-machine-intelligence/api-v1-mcp)

## Channel facts

- Endpoint: `https://horsetruth.com.au/api/v1/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-28.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 56/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 594 tokens (~54/item across 11 items; 11 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Horse Truth Machine Intelligence MCP server?

Horse Truth Machine Intelligence is a hosted endpoint at https://horsetruth.com.au/api/v1/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http au-com-horsetruth-machine-intelligence 'https://horsetruth.com.au/api/v1/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "au-com-horsetruth-machine-intelligence": {
      "url": "https://horsetruth.com.au/api/v1/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "au-com-horsetruth-machine-intelligence": {
      "type": "http",
      "url": "https://horsetruth.com.au/api/v1/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.au-com-horsetruth-machine-intelligence]
url = "https://horsetruth.com.au/api/v1/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "au-com-horsetruth-machine-intelligence": {
      "type": "remote",
      "url": "https://horsetruth.com.au/api/v1/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add au-com-horsetruth-machine-intelligence --url 'https://horsetruth.com.au/api/v1/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  au-com-horsetruth-machine-intelligence:
    url: "https://horsetruth.com.au/api/v1/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "au-com-horsetruth-machine-intelligence": {
      "Transport": "http",
      "Url": "https://horsetruth.com.au/api/v1/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add au-com-horsetruth-machine-intelligence -t streamable-http -u 'https://horsetruth.com.au/api/v1/mcp'
```

### Other

```json
{
  "mcpServers": {
    "au-com-horsetruth-machine-intelligence": {
      "type": "http",
      "url": "https://horsetruth.com.au/api/v1/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-28 (score 69, +3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 66, −2)

- [security] Tool “horse_changes” rewrote its description, which is the text the model reads
- [security] Tool “horse_intelligence” rewrote its description, which is the text the model reads
- [security] Tool “horse_rankings” rewrote its description, which is the text the model reads
- [security] Tool “resolve_horse” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 44 → 54
- [functional] Schema quality: good → fair
- [functional] New tool “horse_compare”
- [functional] New tool “horse_explanation”
- [functional] New tool “horse_provenance”
- [functional] New tool “horse_signal”
- [functional] New tool “horse_snapshot”

### 2026-09-26 (score 68, +1)

- [security] Tool “discover_purchase_options” rewrote its description, which is the text the model reads
- [security] Tool “sandbox_preview” rewrote its description, which is the text the model reads

### 2026-09-25 (score 67, +7)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 60, +27)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 0
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good

### 2026-09-21 (score 33)

First indexed and scored.

## MCP tools (11)

### `discover_purchase_options` (~35 tokens)

FREE: Return the self-service purchase, products, sandbox and checkout navigation needed for an autonomous client to buy Horse Truth machine access.

### `horse_changes` (~55 tokens)

PAID: US$0.02 per successful autonomous x402 call, or 1 Horse Truth direct credit. Return material Horse Truth change events for one horse.

Input parameters:

- `horse` (string, required)
- `limit` (integer)

### `horse_compare` (~48 tokens)

PAID: US$0.02 per successful autonomous x402 call, or 1 Horse Truth direct credit. Compare compact derived snapshots for two to five horses.

Input parameters:

- `horses` (array, required)

### `horse_explanation` (~56 tokens)

PAID: US$0.02 per successful autonomous x402 call, or 1 Horse Truth direct credit. Return a structured explanation of the current derived Horse Truth read without exposing raw provider records.

Input parameters:

- `horse` (string, required)

### `horse_intelligence` (~53 tokens)

PAID: US$0.02 per successful autonomous x402 call, or 1 Horse Truth direct credit. Return derived intelligence for one horse. Raw provider records are not exposed.

Input parameters:

- `horse` (string, required)

### `horse_provenance` (~54 tokens)

PAID: US$0.02 per successful autonomous x402 call, or 1 Horse Truth direct credit. Return a cryptographic receipt for the current derived horse-intelligence payload.

Input parameters:

- `horse` (string, required)

### `horse_rankings` (~54 tokens)

PAID: US$0.02 per successful autonomous x402 call, or 1 Horse Truth direct credit. Return current derived Horse Truth rankings from the already-warmed canonical model cache.

Input parameters:

- `limit` (integer)

### `horse_signal` (~76 tokens)

PAID: US$0.02 per successful autonomous x402 call, or 1 Horse Truth direct credit. Return one named derived Horse Truth signal for a horse, such as readiness, biomechanics, progression, trouble watch, class, reliability, alerts or winning conditions.

Input parameters:

- `horse` (string, required)
- `signal` (string, required)

### `horse_snapshot` (~48 tokens)

PAID: US$0.02 per successful autonomous x402 call, or 1 Horse Truth direct credit. Return a compact derived operating snapshot for one horse.

Input parameters:

- `horse` (string, required)

### `resolve_horse` (~48 tokens)

PAID: US$0.02 per successful autonomous x402 call, or 1 Horse Truth direct credit. Resolve a horse identity against Horse Truth profiles.

Input parameters:

- `query` (string, required)

### `sandbox_preview` (~38 tokens)

FREE: Return a fixed Horse Truth schema/capability preview for Chance With Wolves. No paid entitlement is consumed and no raw provider records are exposed.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/au-com-horsetruth-machine-intelligence/api-v1-mcp#diagnostics

## Score history

- 2026-09-28: 69
- 2026-09-27: 66
- 2026-09-26: 68
- 2026-09-25: 67
- 2026-09-24: 60
- 2026-09-23: 33
- 2026-09-22: 33
- 2026-09-21: 33

## Common questions

### What is the Horse Truth Machine Intelligence MCP server?

Horse Truth Machine Intelligence is an MCP server listed in the public MCP registry as au.com.horsetruth/machine-intelligence. Derived Australian racehorse intelligence for AI agents, MCP clients, software and publishers. This page covers its hosted endpoint (https://horsetruth.com.au/api/v1/mcp).

### Is the Horse Truth Machine Intelligence MCP server safe to use?

Horse Truth Machine Intelligence scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Horse Truth Machine Intelligence MCP server expose?

Horse Truth Machine Intelligence exposes 11 tools: discover_purchase_options, horse_changes, horse_compare, horse_explanation, horse_intelligence, and 6 more. Their descriptions and schemas cost roughly 565 tokens of context every time the server is loaded.

### Does the Horse Truth Machine Intelligence MCP server require authentication?

No. We connected to Horse Truth Machine Intelligence without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Horse Truth Machine Intelligence MCP server still maintained?

Horse Truth Machine Intelligence is still listed as active in the MCP registry. We last reached this channel on 28 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://horsetruth.com.au/api/v1/mcp
- Authorisation metadata: https://horsetruth.com.au/.well-known/oauth-protected-resource/api/v1/mcp
- Changelog RSS feed: https://verifymcp.io/servers/au-com-horsetruth-machine-intelligence/api-v1-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/au-com-horsetruth-machine-intelligence/api-v1-mcp.json
- HTML version of this page: https://verifymcp.io/servers/au-com-horsetruth-machine-intelligence/api-v1-mcp