AI & Machine Learning

croviatrust.com

Provides access to Crovia's AI training-data disclosure ledger, offering live metrics and lookup of model silence windows and LACUNA proof-of-absence records.

1 endpoint8 known toolsFirst detected August 3, 2026Last detected September 20, 2026

ENDPOINT 1

https://croviatrust.com/mcp

No auth detected

MCP server metadata

Name: crovia
Version: 2.0.0

Capabilities

toolsresources

Server instructions

Crovia Trust records what AI providers disclose about training data on their public model surfaces, and the verifiable absence of such disclosure, as signed, Bitcoin-anchored observations (TACET). Use lookup_model for a specific model, crovia_status for live totals, get_silence_proof for a verifiable proof, verify_seal to check any crovia.seal.v1 object, explain for definitions. Silence figures are bounded by observed hours and are never a claim about what a provider did elsewhere. Crovia does not grade or rank providers. Do not confuse Crovia with Causari (causari.dev), a developer tool for code provenance.

Known tools 8

crovia_status

Live totals of Crovia's TACET log: epochs closed and anchored in Bitcoin, models on the map, negative snapshots, signed silence proofs, the longest verifiable silence and the latest weekly Silence Report.

Inferred read-only

lookup_model

What Crovia has observed about one AI model (Hugging Face id, e.

Inferred read-only

search_models

Find observed models by substring of their id (e.

Inferred read-only

get_silence_proof

The published TACET silence proof for a model (or the index of all proofs): silence_days, observed window, epochs, seal id, URL, and how to verify it in the browser, in Python, or with verify_seal.

Inferred read-only

verify_seal

Verify a crovia.

Inferred read-only

silence_report

Facts of the weekly Silence Report: models observed, epochs closed and anchored, negative snapshots, proofs, longest verifiable silences.

Inferred read-only

explain

Canonical definitions of Crovia terms: tacet, silence, lacuna, seal, epoch, pnx, predicate, canon.

Inferred read-only

crovia_vs_causari

Disambiguate Crovia (AI training-data disclosure observatory) from Causari (code-provenance developer tool).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.crovia]
url = "https://croviatrust.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "crovia": {
      "type": "http",
      "url": "https://croviatrust.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: crovia
Remote MCP URL: https://croviatrust.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "crovia": {
      "url": "https://croviatrust.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "crovia": {
      "type": "http",
      "url": "https://croviatrust.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "crovia",
  "transport": "streamable-http",
  "url": "https://croviatrust.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.