# com.arcaneforecasting/world-sense

> Read-only live geopolitical-risk sensing for agents. ARCANE notices; never forecasts or advises.

- name: com.arcaneforecasting/world-sense
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 88/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.arcaneforecasting%2Fworld-sense
- tools: https://api.protogrid.dev/v1/servers/com.arcaneforecasting%2Fworld-sense/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "world-sense": {
      "type": "http",
      "url": "https://mcp.arcaneforecasting.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 65
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-97% ~updated-97d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: arcane_overview (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); arcane_system_status (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); arcane_deltas (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 858 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 10, about 858 tokens to load them all
- tool set hash: f02c5d46fb5f19c6dce8f5aaa7c3319b
- badge: [![protogrid quality](https://protogrid.dev/badge/com.arcaneforecasting/world-sense.svg)](https://protogrid.dev/servers/com.arcaneforecasting/world-sense)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.arcaneforecasting.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.96581197)

## Packages

_none_

## Tools (10)

- `arcane_bilateral`: Observed bilateral signal-intensity across seven tracked country pairs (volume and tone indices, plus an observed escalation stage). An index of observed intensity between the pair, not a prediction of what happens next. Check as_of/stale.
- `arcane_capabilities`: What ARCANE's public World-Sense serves and what it explicitly does NOT serve, plus per-stream validation notes. ARCANE NOTICES present-state geopolitical risk from primary-source senses; it does not forecast, advise, or trade.
- `arcane_data_streams`: Latest observations from ARCANE's primary-source physical senses (energy stocks, fires, sanctions, GPS interference, outages, and more) with provider, cadence, and attribution. Observed levels only; some senses go silent when their baseline saturates. Check as_of/stale.
- `arcane_deltas`: What changed since yesterday across ARCANE's domains and primary-source senses (observed diffs only). Grounding-sense items fire once at onset then go quiet, so absence of an item is not calm. Check as_of/stale.
- `arcane_domain`: Drill-down for one domain: observed risk/momentum series, current-state regime posterior, and news-coverage theme cards (coverage unusualness, not truth or importance). ARCANE NOTICES the present; it does not predict. Check as_of/stale.
- `arcane_overview`: Current ARCANE overview: Combined Threat Score, per-domain risk rows, cascade state, and cross-domain gauges as observed now. ARCANE NOTICES the present; it does not predict or advise. Check as_of/stale before treating as current.
- `arcane_score_tree`: How the Combined Threat Score is composed: per-domain roll-ups, applied premiums, and the design weights behind them, each carrying a live/config provenance tag. Weights are design configuration, not fitted parameters. Check as_of/stale.
- `arcane_system_status`: Freshness of every public ARCANE key: push time, source as_of, and stale flag. Call this before treating any reading as current.
- `arcane_tracker`: ARCANE's live scenario tracker: for each pre-registered scenario, where the world is on its branching map — checkpoint COMPLETION as N/M (confirming signals fired of total), a direction of resemblance, staleness, and which fork checkpoints have fired or are pending. A live STATE view, NOT a forecast: completion is not a probability and direction is resemblance, not odds. ARCANE never states a scenario's likelihood. Check as_of/stale.
- `arcane_trigger_chains`: Observed multi-stage trigger-chain state for five domains (stage activation, z-scores, and chain health). Descriptive state only, not a forecast; the chains were repaired 2026-07-02 and not yet exercised live. Check as_of/stale.