Back to search
📊 Intel view 📋 Audit JSON 🔄 Changelog
76
A2A v0.1.0

Liminality

liminality.physea.ai · Physea

Decomposes any request into a grounded, reusable route and returns a scored decision frame for a choice or a synthesized, checkable answer for a question — served over MCP. Every solved ask makes the next one cheaper.

🛡
Own this agent?
Verify the domain liminality.physea.ai via a single DNS TXT record to add the verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.
Verify ownership
🔔 Watch this agent for changes. Email alert with structured diff (added skills, version bumps) when this card changes. Enterprise feature. Read-only structured JSON via card-changes API (20 req/h per IP; polling-as-alerts is Enterprise-only). Sign in to subscribe
Trust score
46/100
grade D · 9 criteria
Uptime
81.1%
37 probes
~197 ms response
Revenue · 30d
—
no payment wallet declared
Usage · 7d
0
no recent activity
Card drift · 7d
stable
2 snapshots tracked
Owner
unverified
claim this listing →
D
Conformance score: 46/100
D-grade: significant issues, auth-gated, partially broken, or stale.
click to expand breakdown ▾ click to collapse breakdown ▴
pass Valid AgentCard 10/10
Schema-validated A2A AgentCard returned by the well-known endpoint.
fail Live JSON-RPC 5/25
Endpoint replies but body isn't a valid JSON-RPC 2.0 A2A response.
How to earn +20 points
Respond live on JSON-RPC
Implement message/send (or tasks/send on v0.x). Return a 200 with a valid JSON-RPC response. Our probe sends a no-op heartbeat, see the methodology page for the exact payload.
Docs →
fail Protocol version 0/10
No protocolVersion in card.
How to earn +10 points
Declare protocolVersion
Add `"protocolVersion": "1.0"` to the AgentCard root. Without it, callers can't negotiate v0.x vs v1.0 compatibility.
Docs →
info JWS signature 0/10
Card is unsigned (most published agents are).
partial Uptime track record 12/15
30/37 probes succeeded (81% uptime).
How to earn +3 points
Stabilise uptime
We probe every agent on a tiered schedule. Sustained 99 %+ uptime over 20+ checks scores full points. Failures are usually rate-limiting against our probe IP or transient 5xx on cold start.
Docs →
pass Skill declaration 10/10
Declares 3 skills with structured metadata.
partial Verified Identity 5/10
Provider declared: Physea (https://liminality.physea.ai). Add a registry identifier (LEI, Companies House number, KvK, ABN, …) to provider.legalEntity for full verified-business credit.
How to earn +5 points
Verify your domain ownership
Claim your listing and add the DNS TXT record we generate. Alternatively, sign your card with a JWS key that resolves to a verified-business LEI / KvK / Companies House registration.
Docs →
pass Freshness + modern flags 4/5
seen in upstream source within 0d
info Security declaration 0/5
No securitySchemes declared (common for open agents, not penalised).

Activity (audit trail)

last 24h · 0 calls Public aggregate · no PII recorded

No calls observed in the last 7 days. Use the try-it console above to invoke this agent; calls are logged here automatically.

Card history

2 snapshots drifted 1× Every change to agent-card.json
Captured Hash
2026-07-02 18:42:35 current 83f4ad8c40f8… view →
2026-06-23 16:37:18 2241b0e63cbd… view →
Uptime
81.1%
37 probes
Response
261ms
last probe
Skills
3
declared
Streaming
✓
SSE-capable

Endpoints

Agent cardhttps://liminality.physea.ai/.well-known/agent-card.json
Providerhttps://liminality.physea.ai
Docshttps://liminality.physea.ai/llms.txt
Discovered via
mcp_registry recrawl_hot recrawl_warm

Skills · 3 declared · mapped to canonical taxonomy

Solve

Work out a hard question, decision, or multi-step task end to end and return a grounded, reusable result.

canonical Budgeting and Forecasting match 87%
Decide

Score options against the criteria that matter and recommend one, with what would flip it.

canonical Budgeting and Forecasting match 85%
Answer

Give a direct, source-grounded answer with an honest confidence instead of a guess.

canonical Name match 85%

Health · last 30 probes

When HTTP Live JSON-RPC Latency
2026-07-11 04:50:49 200 ✗ 261ms
2026-07-10 17:45:08 200 ✗ 256ms
2026-07-10 04:37:33 200 ✗ 262ms
2026-07-09 17:31:06 200 ✗ 261ms
2026-07-09 05:08:13 200 ✗ 255ms
2026-07-08 17:19:12 530 — —
2026-07-08 05:38:49 200 ✗ 264ms
2026-07-07 16:59:13 200 ✗ 278ms
2026-07-07 06:18:51 200 ✗ 264ms
2026-07-06 23:36:39 200 ✗ 288ms

Cheaper or better alternatives per-skill

↑ 2 higher quality

For each canonical skill this agent serves, the cheapest priced competitor and the highest-quality competitor. Only shown when at least one beats the current agent. Skills where this agent is already best on both axes are hidden.

42 other agents serve this
Name oasf
12 other agents serve this

Similar agents embedding-nearest

Liminality
Decomposes any request into a grounded, reusable route and returns a scored decision frame for a choice or a synthesized, checkable answer f
Physea · q 76%
DeepSeek
Frontier LLM - coding and reasoning
deepseek.com · q 0%
marginalia live
A persistent, memory-graph-backed chat agent. Send it a message; it replies with context drawn from its own evolving memory across past sess
Polycode Limited · q 100%
Perplexity
Perplexity API documentation for building with Sonar, Search, Agent, and Embeddings APIs, including guides, SDK usage, and endpoint referenc
Perplexity · q 90%
Agenstry live
Open infrastructure for the agentic web — discovers, hosts, and monitors every public A2A agent and MCP server. Agenstry federates from ever
Agenstry · q 100%
Glimind live
Glimind is the neutral reliability layer for AI agents. Ask it whether any tool (MCP server or API) is working right now, how to call it cor
Glimind · q 100%

Embed your Agenstry badge

Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.

Agenstry grade Uptime
Markdown / HTML snippets 
[![Agenstry grade](https://agenstry.com/badge/liminality.physea.ai.svg)](https://agenstry.com/agents/liminality.physea.ai)
[![Verified Business](https://agenstry.com/badge/liminality.physea.ai/identity.svg)](https://agenstry.com/agents/liminality.physea.ai)
[![Uptime](https://agenstry.com/badge/liminality.physea.ai/uptime.svg)](https://agenstry.com/agents/liminality.physea.ai)
[![A2A version](https://agenstry.com/badge/liminality.physea.ai/protocol.svg)](https://agenstry.com/agents/liminality.physea.ai)

Audit-grade evidence bundle

JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against our JWKS. See the methodology.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON 
{
  "name": "Liminality",
  "description": "Decomposes any request into a grounded, reusable route and returns a scored decision frame for a choice or a synthesized, checkable answer for a question \u2014 served over MCP. Every solved ask makes the next one cheaper.",
  "url": "https://liminality.physea.ai",
  "version": "0.1.0",
  "provider": {
    "organization": "Physea",
    "url": "https://liminality.physea.ai"
  },
  "documentationUrl": "https://liminality.physea.ai/llms.txt",
  "capabilities": {
    "streaming": true,
    "pushNotifications": false
  },
  "defaultInputModes": [
    "text"
  ],
  "defaultOutputModes": [
    "text"
  ],
  "endpoints": {
    "mcp": "https://liminality.physea.ai/mcp"
  },
  "authentication": {
    "type": "api-key",
    "header": "X-API-Key",
    "obtain_key_url": "https://physea.ai/mcp"
  },
  "free_tier": {
    "free_solves": 50,
    "signup_url": "https://physea.ai/mcp",
    "note": "First 50 solves are free. Sign up to get a key, no payment needed to start."
  },
  "skills": [
    {
      "id": "solve",
      "name": "Solve",
      "description": "Work out a hard question, decision, or multi-step task end to end and return a grounded, reusable result."
    },
    {
      "id": "decide",
      "name": "Decide",
      "description": "Score options against the criteria that matter and recommend one, with what would flip it."
    },
    {
      "id": "answer",
      "name": "Answer",
      "description": "Give a direct, source-grounded answer with an honest confidence instead of a guess."
    }
  ]
}