# Own Your Mind DeAI assessments

> Signed, independent scores and claim checks for decentralised AI projects. Read-only, no auth.

- name: ai.ownyourmind/oym-substrate
- version: 1.1.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 73/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.ownyourmind%2Foym-substrate
- tools: https://api.protogrid.dev/v1/servers/ai.ownyourmind%2Foym-substrate/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "oym-substrate": {
      "type": "http",
      "url": "https://agent-trust.ownyourmind.ai/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 2025-11-25; 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: get_freedom_breakdown (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); compare_projects (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_project_assessment (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 896 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: 7, about 896 tokens to load them all
- tool set hash: 222f141ab6a48e9339d0dbb28c3ef477
- tools last changed: 2026-10-19T04:13:03.668Z
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.ownyourmind/oym-substrate.svg)](https://protogrid.dev/servers/ai.ownyourmind/oym-substrate)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-19 `get_integrity_verdicts` changed (description, inputSchema)
  - before: Every claim we checked for a project against independent data: the reconciliations (reported figure vs our independent value, method, verdict, evidence link), metric flags, and emission honesty. Carries the verdict vocabulary, assessment levels and `_rule` verbatim so a caller reports 'not-assessed' honestly and never invents a 'verified'.
  - after: Every claim we checked for a project against independent data: the reconciliations (reported figure vs our independent value, method, verdict, evidence link), metric flags, and emission honesty. Carries the verdict vocabulary, assessment levels and `_rule` verbatim so a caller reports 'not-assessed' honestly and never invents a 'verified'. Optional verdict filter (e.g. 'inflated', 'outdated') narrows the rows. Paged at 25 rows: when next_offset is set, call again with offset=next_offset.
- 2026-10-19 `get_project_assessment` changed (description, inputSchema) **meaning changed**
  - before: The full signed substrate record for one project: dual scores + breakdowns, integrity reconciliations, data sources and primary-data snapshot, plus the attestation envelope (substrate_hash + per-project ed25519 signature).
  - after: One project's assessment: dual scores + breakdowns, integrity level, verdict counts and every checked claim or finding in brief, plus review_url to cite and the attestation envelope. full=true returns the whole signed record instead (adds data sources and the primary-data snapshot; over 100K characters for the deepest reviews).

Full history: https://api.protogrid.dev/v1/servers/ai.ownyourmind%2Foym-substrate/changes

## Remotes

- https://agent-trust.ownyourmind.ai/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (7)

- `compare_projects`: Compare several projects on one axis ('freedom' or 'returns'), aligned per
    dimension so an agent can rank them like-for-like. Returns each project's per-
    dimension score/max, total, grade and assessment level.
- `get_agent_trust_snapshot`: The latest OYM agent-trust index summary (ERC-8004 agent identity, reputation and
    x402 settlement reconciliation): observations with a methodology version and scope
    notes, never verdicts. Carries `data_as_of` — this data refreshes only periodically.
- `get_freedom_breakdown`: The 6-dimension Freedom score for a project (infrastructure, governance, token
    distribution, censorship resistance, data sovereignty, open source), each with
    score/max and the evidence behind it, plus grade and total /100.
- `get_integrity_verdicts`: Every claim we checked for a project against independent data: the reconciliations
    (reported figure vs our independent value, method, verdict, evidence link), metric
    flags, and emission honesty. Carries the verdict vocabulary, assessment levels and
    `_rule` verbatim so a caller reports 'not-assessed' honestly and never invents a
    'verified'. Optional verdict filter (e.g. 'inflated', 'outdated') narrows the rows.
    Paged at 25 rows: when next_offset is set, call again with offset=next_offset.
- `get_project_assessment`: One project's assessment: dual scores + breakdowns, integrity level, verdict
    counts and every checked claim or finding in brief, plus review_url to cite and the
    attestation envelope. full=true returns the whole signed record instead (adds data
    sources and the primary-data snapshot; over 100K characters for the deepest reviews).
- `get_returns_breakdown`: The 5-dimension Returns score for a project (token utility, value accrual, supply
    dynamics, revenue sustainability, liquidity & access), each with score/max and
    evidence, plus grade and total /100.
- `list_projects`: List every assessed decentralised AI project with its dual scores, grades and
    assessment level. Optional filters: category (compute|data|inference|storage|
    agent|platform|other) and status (e.g. active). Returns summaries only; call
    get_project_assessment for the full record. `_rule` states the honesty contract.