Artificial eXperience Intelligence (AXI)

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

AXI design reviews, gated AXI Score, and paper search for AI assistants, agents, and robots.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Artificial eXperience Intelligence (AXI)": {
      "url": "https://axi.sripto.tech/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (6)

• axi_get_definition read-only

  Return the definition of Artificial eXperience Intelligence (AXI) from the v2.0 paper, its author, citation, and disambiguation from similarly named terms (e.g. the Arm AMBA AXI bus).

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• axi_calculate_score read-only

  Compute the multiplicative gated AXI Score (AXI v2.0, Section 4.5.8) from telemetry metrics. Consent and integrity gates fail closed when data is missing.

  Parameters:

  • cf (required) — object — Consent Fidelity per event class (0–1). Missing values fail the gate closed.
  • ii — number — Interaction Integrity (0–1). Alternatively pass integrity sub-scores.
  • pc — number — Presence Continuity (0–1)
  • re — number — Repair Efficacy (0–1)
  • cli — number — Cognitive Load Index (0–100)
  • tdr — number — Trust Decay Rate in trust-index points/day
  • ttc — number — Time-to-Comfort in seconds
  • integrity — object — Sub-scores used to compute II by weighted harmonic mean when ii is omitted

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• axi_calculate_autonomy_score read-only

  Compute AXI_A for robotaxis, driver-assistance, delivery robots, and humanoids: safety-case, bystander-legibility, consent, and integrity gates times the episode-weighted role BaseScore.

  Parameters:

  • cf (required) — object — Consent Fidelity per event class (0–1). Missing values fail the gate closed.
  • safetyCase (required) — boolean — Deployment holds a valid external safety case or type approval for its ODD
  • bystanderLegibility (required) — number — Bystander Legibility (0–1); gate requires >= 0.95
  • ii — number — Interaction Integrity (0–1). Alternatively pass integrity sub-scores.
  • roles — array — Role-level metrics (principal, supervisor, occupant). Give baseScore directly or the metrics.
  • integrity — object — Sub-scores used to compute II by weighted harmonic mean when ii is omitted

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• axi_design_review read-only

  Given a description of an AI system (assistant, coding agent, voice bot, background agent, robot, vehicle), return the applicable AXI conformance profile, Bridge components, guardrails, and black-box conformance tests to include in its design and plan.

  Parameters:

  • system_description (required) — string — What the AI system does, who uses it, and what actions it can take
  • profile — string — Force a profile instead of inferring one

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• axi_search_paper read-only

  Full-text search over the AXI v2.0 research paper. Returns the most relevant sections with headings for grounding and citation.

  Parameters:

  • query (required) — string
  • limit — integer

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• axi_cite read-only

  Return a citation for the AXI paper in text, APA, or BibTeX format.

  Parameters:

  • format — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

Publisher website

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