MCP serverai.physea/liminality
Breaks a hard question or decision into checkable sub-questions, grounds each to a real tool.
Overview
Score?
UNRATED 0.528
of what a free look can see, on 16 looks
Looks
28
last 1 day ago
Tools
27
changed 19 days ago
More info
URL
liminality.physea.ai/mcp
streamable-http
Says it is
Liminality 1.27.2
protocol 2025-06-18
In the record since
32 days ago
Among servers18,413 with a card
0median 0.606 · this server 0.528 · highest on record 0.8561
Toolsfrom sha256:29f5feba93…ff443b · +0 −0 19 days ago
| Tool | Schema |
|---|---|
| algorithms 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. |
input · no output |
| apply_form Apply form answers to sharpen a task. |
input · no output |
| apply_grade Apply a grade-form answer to a result. |
input · no output |
| ask_form Create a short form for missing user-specific facts. |
input · no output |
| catalog Read the capability catalog: action='search' returns every saved candidate for an objective with distinctiveness deltas; action='delta' compares a named entity pair. |
input · no output |
| composio_connect Create a caller-scoped connection link for a toolkit. |
input · no output |
| compress_context Compress long context into a task-focused brief; use before reading any source over 8,000 characters. |
input · no output |
| delegation Create, resume, or report a bounded subagent packet (action='create'|'resume'|'report'). |
input · no output |
| export_result Export a caller-owned result in a supported format. |
input · no output |
| get_capabilities List solve modes and every public capability. |
input · no output |
| get_result_detail Fetch the full caller-owned result behind a lean solve. |
input · no output |
| get_settings Read this caller's saved solve and safety settings. |
input · no output |
| handoff Create, safely resume, or list caller-scoped cross-session checkpoints (action='create'|'resume'|'list'). Create accepts an optional subject and source_sessions; Liminality assigns |
input · no output |
| manage Compatibility router for retained-context lifecycle actions. |
input · no output |
| optimize Rank bounded one-factor variants for a route against your stated objective; candidates remain unsaved. |
input · no output |
| recover 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= |
input · no output |
| register_asset Register a caller-owned resource for future grounding. |
input · no output |
| report_feedback Report structured feedback on a result. |
input · no output |
| report_outcome Report verified real-world outcome evidence for a result. |
input · no output |
| research Run a multi-source research pass for a question. |
input · no output |
| runs Run lifecycle with run and attempt identity (action='start'|'status'|'list'|'cancel'|'reconcile'|'attempt'|'execute'|'outcome'|'approve'|'grants'|'revoke'): cancel persists, an unk |
input · no output |
| set_priorities Save caller-scoped tasks and importance signals. |
input · no output |
| set_settings Save caller-scoped settings from one dict (depth, optimization, trace, relay, governance); keys and values in get_capabilities. |
input · no output |
| setup Context-minimality setup with no questions (auto); or profiles, status, verify. |
input · no output |
| solve Decompose, ground, and answer a non-trivial task. Supports saved or per-call depth, safe trace, caller tools, and lean/full output. |
input · no output |
| task Read or version the contract behind a solve (action='get'|'list'|'versions'|'new_version'|'graph'|'create'|'state'); graph also returns what is still unfinished. |
input · no output |
| taxis Return this caller's deterministic ranked priority frame. |
input · no output |
Verify it yourself
npx teppi-check https://liminality.physea.ai/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ22GWHF6ESKDTGC9Y69RH