_ registry / mcp streamable-http · checked 6h ago

WELL

https://well.arif-fazil.com

Registry code: f33f72c40bdbc9b5

api record

WELL is the Universal Substrate Vitality Mirror for arifOS. H-WELL reflects operator Arif's biological and cognitive state. M-WELL reflects system reliability, tool health, context integrity, and compute limits. G-WELL reflects machine governance health -- autonomic coherence, check/balance integrity, floor compliance. C-WELL evaluates coupled risk between human state and machine state. U-WELL (Universal) classifies any substance or substrate and assesses vitality without category error, authority overreach, or false equivalence. The WELL-FORGE bridge lets A-FORGE adapt execution intensity to…

endpoint
https://well.arif-fazil.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is WELL live?
Yes — it answered the hub's last check (checked 6h ago). It answered 97% of checks over the last 30 days.
Is WELL free to use?
Yes — the hub reached it with no key and no payment.
What tools does WELL have?
10 tools: well_machine_diagnose, well_assess_reliability, well_trace_lineage, well_guard_dignity, well_classify_substrate, well_assess_homeostasis, well_machine_recommend, well_check_repair, ….
Is WELL safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
96.6%

90 days 97.1%· all time 97.1%

latency
652ms

last good check

priced tools
0

of 10 tools

_ answered our checks, 90 days 583 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
topic
infrastructure & devops monitoring & observability
used for
  • diagnose vps machine health
  • get fix recommendations for machine issues
  • check tool registry status
  • assess system reliability
takes → gives
text → data, text
tools
10 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 10 tools
10 open 10 of 10 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • well_machine_diagnose reads open 15h ago

    M-WELL MACHINE DIAGNOSTIC -- Full VPS health with actionable recommendations. Reads machine_state.json (cron-collected /proc telemetry every 5 min). Returns: CPU, RAM, swap, disk, PSI pressure, services, Docker, zombies. Includes per-issue RECOMMENDATIONS suitable for A-FORGE routing. P0 EVIDENCE HONESTY (well-evidence-honesty/v1): - readiness is TASK-SCOPED. Pass task_id or task_class; without a task scope the readiness state is UNKNOWN -- system metrics never imply task readiness. For recovery-scoped checks use task_id="recovery:<target>". - recovery_receipt: an independent observation receipt (never an executor success payload). recovery_verified stays false unless the receipt is valid, fresh, on-target and non-self-witnessed. This is the CANONICAL M_WELL diagnostic -- use this instead of well_assess_reliability for VPS optimization workflows.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "task_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "actor_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "task_class": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "recovery_receipt": {
      "anyOf": [
        {
          "type": "object",
          "additionalProperties": true
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}
    arguments 51 lines
  • well_assess_reliability reads open 15h ago

    Ω-WELL-10: Assess machine, tool, institution, and operational reliability.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "default": "health"
    },
    "actor_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
  • well_trace_lineage reads open 23h ago

    Ω-WELL-02: Memory, trend, ledger, and vault chain tracing.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "default": "recall"
    },
    "force": {
      "type": "boolean",
      "default": false
    },
    "limit": {
      "type": "integer",
      "default": 10
    },
    "reason": {
      "type": "string",
      "default": "state_checkpoint"
    },
    "dry_run": {
      "type": "boolean",
      "default": false
    },
    "actor_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "lookback_days": {
      "type": "integer",
      "default": 30
    }
  },
  "additionalProperties": false
}
    arguments 41 lines
  • well_guard_dignity reads open 32h ago

    Ω-WELL-12: Guard soul, personhood, meaning, and symbolic boundaries. INTEGRATION (2026-09-19): this tool is BOTH WELL's dignity guard surface AND the REPORT point where a sentence about a person is returned as an assessment that drives a recommendation. The claim-class gate is therefore integrated HERE rather than sitting beside the guard: * the gate CONSUMES this guard's verdict (``assess_dignity_risk``) — it never re-implements it, and a guard tier of HOLD forces the gate closed; * the guard can only ever REMOVE assessment eligibility, never grant it; * the guard's at-risk verdict is NEVER withheld, softened or overridden — a HOLD is a safety output, not an assessment about the person; * ``person_label_assigned`` is always False: only the SENTENCE carries a class, never the human being it is about.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "default": "consent"
    },
    "subject": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "actor_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "claim_class": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "coercion_signals": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "reductionism_risk": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "dignity_preservation": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}
    arguments 79 lines
  • well_classify_substrate reads open 6h ago

    Ω-WELL-01: Substrate classification and boundary sensing.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "default": "classification"
    },
    "subject": {
      "type": "string",
      "default": ""
    },
    "actor_id": {
      "type": "string",
      "default": "well-substrate"
    },
    "session_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "description": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "evaluation_intent": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}
    arguments 51 lines
  • well_assess_homeostasis reads open 6h ago

    Ω-WELL-06: Assess regulation, stability, and empathic balance under change. When mode="fatigue", accepts biometric overrides to support contrast scenarios and real-time assessment without state.json dependency. Also accepts decision_class to route the homeostasis verdict through the C-class threshold matrix: C1/C2 -- proceed unless CRITICAL C3 -- proceed if STABLE or better C4 -- proceed only if OPTIMAL; DEFER if STABLE; ADVISORY_BLOCK if DEGRADED/CRITICAL C5 -- proceed only if OPTIMAL + no chronic fatigue; block otherwise

    mcp-tool

    {
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "default": "sleep"
    },
    "subject": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "actor_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "hrv_status": {
      "type": "string",
      "default": "normal"
    },
    "sleep_hours": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "stress_load": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "decision_class": {
      "type": "string",
      "default": "C3"
    },
    "chronic_fatigue": {
      "type": "boolean",
      "default": false
    },
    "emotional_state": {
      "type": "string",
      "default": "neutral"
    },
    "sleep_debt_days": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "coercion_signals": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "decision_fatigue": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "readiness_inputs": {
      "anyOf": [
        {
          "type": "object",
          "additionalProperties": true
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "cognitive_clarity": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "reductionism_risk": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "dignity_preservation": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "accumulated_session_fatigue": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}
    arguments 162 lines
  • well_machine_recommend reads open 15h ago

    M-WELL RECOMMENDATION ENGINE -- Get specific fix commands for machine issues. Maps a diagnosis to concrete shell commands with risk assessment. Modes: swap | memory | disk | service | docker | zombie | all Returns commands suitable for A-FORGE forge_shell execution. ADVISORY_ONLY -- WELL does not execute.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "actor_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "issue_type": {
      "type": "string",
      "default": "swap"
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
  • well_check_repair reads open 6h ago

    Ω-WELL-07: Check repair, recovery, resilience, and forge cycle integrity.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "default": "precheck"
    },
    "source": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "outcome": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "actor_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "intensity": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "decision_class": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "task_description": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}
    arguments 76 lines
  • well_validate_vitality reads open 23h ago

    Ω-WELL-08: Validate vitality, readiness, and NIAT. (Floor compliance removed -- arifOS adjudicates floors.)

    mcp-tool

    {
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "default": "readiness"
    },
    "intent": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "context": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "actor_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "reversibility": {
      "type": "string",
      "default": "unknown"
    },
    "decision_class": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "task_description": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}
    arguments 69 lines
  • well_registry_status reads open 32h ago

    WELL registry truth diagnostic -- blueprint canonical format. Performs live callable tests against all known WELL tool names. Returns structured drift report: intended vs registered vs callable. This is the WELL_REGISTRY tool from the WELL MCP Constitution blueprint. No WELL is healthy without knowing its own organs.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "mode": {
      "enum": [
        "status",
        "full"
      ],
      "type": "string",
      "default": "status",
      "description": "\"status\" = counts + verdict (default). \"full\" = include dry-call detail."
    },
    "actor_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "trace_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "session_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}
    arguments 48 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id f33f72c40bdbc9b5.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/f33f72c40bdbc9b5/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/f33f72c40bdbc9b5/badge.svg)](https://brick.blue/agent/f33f72c40bdbc9b5?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.

_ also on arif-fazil.com 7 entries

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.