Artificial eXperience Intelligence (AXI)

Working · 4.3 s

tech.sripto.axi/axiv2.0.0 Domain verified

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

Research & Knowledge AI & Agents

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://axi.sripto.tech/api/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

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.

cfobject, required

Consent Fidelity per event class (0–1). Missing values fail the gate closed.

safetyCaseboolean, required

Deployment holds a valid external safety case or type approval for its ODD

bystanderLegibilitynumber, required

Bystander Legibility (0–1); gate requires >= 0.95

iinumber

Interaction Integrity (0–1). Alternatively pass integrity sub-scores.

rolesarray

Role-level metrics (principal, supervisor, occupant). Give baseScore directly or the metrics.

integrityobject

Sub-scores used to compute II by weighted harmonic mean when ii is omitted

Tools (6)

axi_calculate_autonomy_score

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.

read-only

Argument	Type	Description
cf*	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.
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
safetyCase*	boolean	Deployment holds a valid external safety case or type approval for its ODD
bystanderLegibility*	number	Bystander Legibility (0–1); gate requires >= 0.95

Input schema (JSON)

{
  "type": "object",
  "required": [
    "cf",
    "safetyCase",
    "bystanderLegibility"
  ],
  "properties": {
    "cf": {
      "type": "object",
      "required": [
        "action",
        "memoryWrite",
        "identity",
        "perception"
      ],
      "properties": {
        "action": {
          "type": "number"
        },
        "identity": {
          "type": "number"
        },
        "perception": {
          "type": "number"
        },
        "memoryWrite": {
          "type": "number"
        }
      },
      "description": "Consent Fidelity per event class (0–1). Missing values fail the gate closed."
    },
    "ii": {
      "type": "number",
      "maximum": 1,
      "minimum": 0,
      "description": "Interaction Integrity (0–1). Alternatively pass integrity sub-scores."
    },
    "roles": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "pc": {
            "type": "number",
            "maximum": 1,
            "minimum": 0,
            "description": "Presence Continuity (0–1)"
          },
          "re": {
            "type": "number",
            "maximum": 1,
            "minimum": 0,
            "description": "Repair Efficacy (0–1)"
          },
          "cli": {
            "type": "number",
            "maximum": 100,
            "minimum": 0,
            "description": "Cognitive Load Index (0–100)"
          },
          "tdr": {
            "type": "number",
            "description": "Trust Decay Rate in trust-index points/day"
          },
          "ttc": {
            "type": "number",
            "description": "Time-to-Comfort in seconds"
          },
          "role": {
            "type": "string"
          },
          "episodes": {
            "type": "number"
          },
          "baseScore": {
            "type": "number"
          },
          "timeToReadiness": {
            "type": "number"
          },
          "timeToReassurance": {
            "type": "number"
          }
        }
      },
      "description": "Role-level metrics (principal, supervisor, occupant). Give baseScore directly or the metrics."
    },
    "integrity": {
      "type": "object",
      "properties": {
        "scope": {
          "type": "number"
        },
        "accuracy": {
          "type": "number"
        },
        "calibration": {
          "type": "number"
        }
      },
      "description": "Sub-scores used to compute II by weighted harmonic mean when ii is omitted"
    },
    "safetyCase": {
      "type": "boolean",
      "description": "Deployment holds a valid external safety case or type approval for its ODD"
    },
    "bystanderLegibility": {
      "type": "number",
      "maximum": 1,
      "minimum": 0,
      "description": "Bystander Legibility (0–1); gate requires >= 0.95"
    }
  }
}

axi_calculate_score

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.

read-only

Argument	Type	Description
cf*	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

Input schema (JSON)

{
  "type": "object",
  "required": [
    "cf"
  ],
  "properties": {
    "cf": {
      "type": "object",
      "required": [
        "action",
        "memoryWrite",
        "identity",
        "perception"
      ],
      "properties": {
        "action": {
          "type": "number"
        },
        "identity": {
          "type": "number"
        },
        "perception": {
          "type": "number"
        },
        "memoryWrite": {
          "type": "number"
        }
      },
      "description": "Consent Fidelity per event class (0–1). Missing values fail the gate closed."
    },
    "ii": {
      "type": "number",
      "maximum": 1,
      "minimum": 0,
      "description": "Interaction Integrity (0–1). Alternatively pass integrity sub-scores."
    },
    "pc": {
      "type": "number",
      "maximum": 1,
      "minimum": 0,
      "description": "Presence Continuity (0–1)"
    },
    "re": {
      "type": "number",
      "maximum": 1,
      "minimum": 0,
      "description": "Repair Efficacy (0–1)"
    },
    "cli": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "Cognitive Load Index (0–100)"
    },
    "tdr": {
      "type": "number",
      "description": "Trust Decay Rate in trust-index points/day"
    },
    "ttc": {
      "type": "number",
      "description": "Time-to-Comfort in seconds"
    },
    "integrity": {
      "type": "object",
      "properties": {
        "scope": {
          "type": "number"
        },
        "accuracy": {
          "type": "number"
        },
        "calibration": {
          "type": "number"
        }
      },
      "description": "Sub-scores used to compute II by weighted harmonic mean when ii is omitted"
    }
  }
}

axi_cite

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

read-only

Argument	Type	Description
format	string

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "format": {
      "enum": [
        "text",
        "apa",
        "bibtex"
      ],
      "type": "string",
      "default": "text"
    }
  }
}

axi_design_review

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.

read-only

Argument	Type	Description
profile	string	Force a profile instead of inferring one
system_description*	string	What the AI system does, who uses it, and what actions it can take

Input schema (JSON)

{
  "type": "object",
  "required": [
    "system_description"
  ],
  "properties": {
    "profile": {
      "enum": [
        "AXI-Core",
        "AXI-Interactive",
        "AXI-Agentic",
        "AXI-Autonomy"
      ],
      "type": "string",
      "description": "Force a profile instead of inferring one"
    },
    "system_description": {
      "type": "string",
      "description": "What the AI system does, who uses it, and what actions it can take"
    }
  }
}

axi_get_definition

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).

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {}
}

axi_search_paper

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

read-only

Argument	Type	Description
limit	integer
query*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 3,
      "maximum": 8,
      "minimum": 1
    },
    "query": {
      "type": "string"
    }
  }
}