mcpbeat Sign in

Liminality MCP Server

by physea Your server? Claim it
answering

Liminality is answering right now. Last checked 7 min ago. It exposes 27 tools. Last commit 7 Sep 2026.

Breaks a hard question or decision into checkable sub-questions, grounds each to a real tool.

Uptime history 47 days of history · worst day 52%
47 days agonow
100.0%
Uptime 24h
92 of 92 checks
27
Tools
read from the server
505 ms
Response time
average over 24h
0
Stars
last commit 7 Sep 2026

What changed 18

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 7 September 2026. No other catalogue keeps this.

15 Sep a tool description was rewritten runs
15 Sep a tool changed the parameters it asks for runs
9 Sep 2 tool descriptions were rewritten compress_context, setup
9 Sep a tool changed the parameters it asks for setup
9 Sep a tool appeared setup
7 Sep 5 tools changed the parameters they ask for algorithms, export_result, handoff and 2 more
7 Sep 4 tools appeared algorithms, recover, runs and 1 more
7 Sep 3 tool descriptions were rewritten algorithms, handoff, task

Nothing serious here today

Today is the operative word: we check Liminality every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.

run in your terminal
claude mcp add liminality --transport http https://liminality.physea.ai/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "liminality": {
      "url": "https://liminality.physea.ai/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.liminality]
url = "https://liminality.physea.ai/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "liminality": {
      "url": "https://liminality.physea.ai/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "liminality": {
      "url": "https://liminality.physea.ai/mcp"
    }
  }
}

Available tools 27

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

apply
apply_form
Apply form answers to sharpen a task.
apply_grade
Apply a grade-form answer to a result.
report
report_feedback
Report structured feedback on a result.
report_outcome
Report verified real-world outcome evidence for a result.
settings
get_settings
Read this caller's saved solve and safety settings.
set_settings
Save caller-scoped settings from one dict (depth, optimization, trace, relay, governance); keys and values in get_capabilities.
algorithms
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.
ask
ask_form
Create a short form for missing user-specific facts.
capabilities
get_capabilities
List solve modes and every public capability.
catalog
catalog
Read the capability catalog: action='search' returns every saved candidate for an objective with distinctiveness deltas; action='delta' compares a named entity pair.
composio
composio_connect
Create a caller-scoped connection link for a toolkit.
compress
compress_context
Compress long context into a task-focused brief; use before reading any source over 8,000 characters.
delegation
delegation
Create, resume, or report a bounded subagent packet (action='create'|'resume'|'report').
export
export_result
Export a caller-owned result in a supported format.
handoff
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 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.
manage
manage
Compatibility router for retained-context lifecycle actions.
optimize
optimize
Rank bounded one-factor variants for a route against your stated objective; candidates remain unsaved.
priorities
set_priorities
Save caller-scoped tasks and importance signals.
recover
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='open'|'candidates'|'choose'|'retry'|'verify'|'add_candidate'|'get'|'list').
register
register_asset
Register a caller-owned resource for future grounding.
research
research
Run a multi-source research pass for a question.
result
get_result_detail
Fetch the full caller-owned result behind a lean solve.
runs
runs
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.
setup
setup
Context-minimality setup with no questions (auto); or profiles, status, verify.
solve
solve
Decompose, ground, and answer a non-trivial task. Supports saved or per-call depth, safe trace, caller tools, and lean/full output.
task
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.
taxis
taxis
Return this caller's deterministic ranked priority frame.

Endpoints

URLTransportStateLatencyChecked
https://liminality.physea.ai/mcp streamable-http answering 552 ms 7 min ago

Alternatives to Liminality

same job, measured the same way
O'Reilly Expert MCP Server
by oreillymedia

Grounded, citable answers to tech questions from O'Reilly's library. Requires Expert MCP access.

answering
Toki Toki
by xfloukiex-lab

A local causality ledger: records decisions and the reasons, for an agent to recall.

50 installs/wk local only
Interview Mode
by teabagkim

Structured interviewer for Claude Code — probing questions, decision tracking, evolving checkpoints.

33 installs/wk local only
OntoRamp Decision Intelligence
by ontoramp

Log, evaluate, and ground AI decisions against authority context. Returns PASS, WARN, or BLOCK.

answering
Smoke Signal
by smoke-signal-app

Phone notifications and phone-answered questions for AI agents: notify and decision-request tools.

local only
Nodedex
by nodedex

Your project's decision history for agents: decisions, dead-ends, constraints - queryable, local.

100 installs/wk local only
Cybersecurity News & Breach Alerts — buy per-query in-session (bleepingwatch)
by a2awire

Cybersecurity news & breach alerts: hacks, patches. Register in-session — free testnet funds.

16 tools answering
No-Shell Agent Architect MCP
by loved0543-dotcom

Turns vague automation requests into tool stacks, prompts, QA checks, and human boundaries.

7 tools answering

Liminality — questions

Answers built from our own checks of this server.

What can Liminality do?
It exposes 27 tools, read directly from the server on our last check. Among them: algorithms, apply_form, apply_grade, ask_form, catalog, composio_connect and 21 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
What is Liminality mostly used for?
Its tools cluster around report, settings and apply. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is Liminality working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 505 ms. The bar chart above shows every period we have measured.
How do I connect Liminality?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Liminality need an API key?
No. Liminality completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 27 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Liminality?
It answers our handshake in 505 ms on average, which is faster than 28% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Liminality open source?
We cannot say either way: 0 stars on GitHub, but we could not determine the licence, and without one the code is not open source by default.