Own Your Mind DeAI assessments

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

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

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Own Your Mind DeAI assessments": {
      "url": "https://agent-trust.ownyourmind.ai/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (7)

• 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.

  Parameters:

  • status
  • category

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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).

  Parameters:

  • slug (required) — string
  • full — boolean

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Parameters:

  • slug (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Parameters:

  • slug (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Parameters:

  • slug (required) — string
  • limit — integer
  • offset — integer
  • verdict

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Parameters:

  • slugs (required) — array
  • axis — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.