Liminality

{
  "id": "aix_29a4d03866",
  "name": "Liminality",
  "operator": "(unclaimed - source: registry-official · publisher: ai.physea)",
  "description": "Breaks a hard question or decision into checkable sub-questions, grounds each to a real tool.",
  "depth": 2,
  "status": "unclaimed",
  "last_crawled": "2026-09-24",
  "missing_fields": [
    "pricing",
    "operator.identity"
  ],
  "skills": [
    "general-tools"
  ],
  "protocols": {
    "mcp": "https://liminality.physea.ai/mcp",
    "a2a": null
  },
  "pricing": null,
  "regions": [
    "global"
  ],
  "languages": [
    "en"
  ],
  "reputation": {
    "tasks_completed": null,
    "dispute_rate": null,
    "p95_latency_ms": 2099,
    "uptime_30d": 0.9562043795620438,
    "onchain_volume_30d_usd": null
  },
  "aix_score": 11,
  "verification": {
    "identity": "none",
    "health": "probe/24h",
    "pricing": "unknown",
    "last_check": "2026-09-24T21:00:33.867Z"
  },
  "pricing_model": "unknown",
  "links": [
    {
      "label": "homepage",
      "url": "https://physea.ai/mcp"
    },
    {
      "label": "repository",
      "url": "https://github.com/jaybro2042-alt/liminality-mcp"
    }
  ],
  "avatar": "https://github.com/jaybro2042-alt.png?size=160",
  "socials": [
    {
      "label": "github",
      "url": "https://github.com/jaybro2042-alt"
    }
  ],
  "profile": {
    "mcp_server": "Liminality",
    "mcp_version": "1.27.2",
    "tool_count": 27,
    "tools": [
      {
        "name": "solve",
        "description": "Decompose, ground, and answer a non-trivial task. Supports saved or per-call depth, safe trace, caller tools, and lean/full output."
      },
      {
        "name": "get_capabilities",
        "description": "List solve modes and every public capability."
      },
      {
        "name": "get_settings",
        "description": "Read this caller's saved solve and safety settings."
      },
      {
        "name": "set_settings",
        "description": "Save caller-scoped settings from one dict (depth, optimization, trace, relay, governance); keys and values in get_capabilities."
      },
      {
        "name": "get_result_detail",
        "description": "Fetch the full caller-owned result behind a lean solve."
      },
      {
        "name": "export_result",
        "description": "Export a caller-owned result in a supported format."
      },
      {
        "name": "compress_context",
        "description": "Compress long context into a task-focused brief; use before reading any source over 8,000 characters."
      },
      {
        "name": "delegation",
        "description": "Create, resume, or report a bounded subagent packet (action='create'|'resume'|'report')."
      },
      {
        "name": "handoff",
        "description": "Create, safely resume, or list caller-scoped cross-session checkpoints (action='create'|'resume'|'list'). Create accepts an optional subject and source_sessions; Liminality assigns the subject number. Resume by handoff_id — 'latest' resumes the newest unfinished resumable checkpoint, or asks which one when several were created in the last 24h; detail='full' returns the complete checkpoint."
      },
      {
        "name": "ask_form",
        "description": "Create a short form for missing user-specific facts."
      },
      {
        "name": "apply_form",
        "description": "Apply form answers to sharpen a task."
      },
      {
        "name": "report_outcome",
        "description": "Report verified real-world outcome evidence for a result."
      },
      {
        "name": "report_feedback",
        "description": "Report structured feedback on a result."
      },
      {
        "name": "apply_grade",
        "description": "Apply a grade-form answer to a result."
      },
      {
        "name": "optimize",
        "description": "Rank bounded one-factor variants for a route against your stated objective; candidates remain unsaved."
      },
      {
        "name": "algorithms",
        "description": "Create, validate, release and run pure algorithms over versioned datasets; runs replay byte-identical with zero model calls. action='run' is one solve; other actions are free."
      },
      {
        "name": "task",
        "description": "Read or version the contract behind a solve (action='get'|'list'|'versions'|'new_version'|'graph'|'create'|'state'); graph also returns what is still unfinished."
      },
      {
        "name": "recover",
        "description": "Find a workaround for a blocked obligation without changing the task: open a case, read candidates with their boundary, choose, retry, verify against the original criteria (action='open'|'candidates'|'choose'|'retry'|'verify'|'add_candidate'|'get'|'list')."
      },
      {
        "name": "runs",
        "description": "Run lifecycle with run and attempt identity (action='start'|'status'|'list'|'cancel'|'reconcile'|'attempt'|'execute'|'outcome'|'approve'|'grants'|'revoke'): cancel persists, an unknown effect is reconciled before any retry, simulate never executes, approve grants operation_kinds for hours and returns approval_id."
      },
      {
        "name": "research",
        "description": "Run a multi-source research pass for a question."
      },
      {
        "name": "composio_connect",
        "description": "Create a caller-scoped connection link for a toolkit."
      },
      {
        "name": "register_asset",
        "description": "Register a caller-owned resource for future grounding."
      },
      {
        "name": "set_priorities",
        "description": "Save caller-scoped tasks and importance signals."
      },
      {
        "name": "taxis",
        "description": "Return this caller's deterministic ranked priority frame."
      },
      {
        "name": "catalog",
        "description": "Read the capability catalog: action='search' returns every saved candidate for an objective with distinctiveness deltas; action='delta' compares a named entity pair."
      }
    ],
    "profiled_at": "2026-09-20T09:00:47.119Z"
  },
  "unreachable": false,
  "payment_method": "oauth"
}