# QSIG Intelligence

> Geopolitical risk score and theme board. Published kill criterion. Measured state, not forecasts.

- name: net.qsig.x402/mcp
- version: 1.1.0
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 73/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/net.qsig.x402%2Fmcp
- tools: https://api.protogrid.dev/v1/servers/net.qsig.x402%2Fmcp/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "x402": {
      "type": "http",
      "url": "https://x402.qsig.net/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-98% +updated-21d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 73/100 (needs work)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### 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: get_geo_themes (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_track_record (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_geo_themes (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 756 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 50 (weight 15)

- pass `stability.changes`: 3 tool changes in 30 days
- fail `stability.rug_pull`: 1 tools kept their name but changed most of their description in 30 days; review before trusting them

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

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

- tools: 5, about 756 tokens to load them all
- tool set hash: 78de0868cd5546bb8fbacb876ce57277
- tools last changed: 2026-09-29T07:49:57.072Z
- badge: [![protogrid quality](https://protogrid.dev/badge/net.qsig.x402/mcp.svg)](https://protogrid.dev/servers/net.qsig.x402/mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-09-29 `get_method` changed (description) **meaning changed**
  - before: Free. How the georisk score is built, what it does and does not claim, pricing, and the payment network.
  - after: Free. What QSIG sells - the georisk score and the geopolitical theme board (get_geo_themes) - what each does and does not claim, pricing, and the payment network.
- 2026-09-29 `list_geo_themes` added
  - Free. Theme keys, labels, linked assets, coverage (qualifying markets, whale USD held, sufficient flag), method version and field notes for get_geo_themes. Use it to decide whether a paid call is worth making.
- 2026-09-29 `get_geo_themes` added
  - QSIG geopolitical theme board. For each theme (HORMUZ_OIL, IRAN, LEVANT, RUSSIA_UKRAINE, CHINA_TAIWAN, FED, CRYPTO): the Polymarket crowd stress index and its 24h / 7d change on the same markets, tracked whale positions and 24h flows (aggregates only, no wallet addresses), the news-event count against its same-window baseline, and the top 3 markets. theme is an optional key; omit it for all themes. as_of is an optional ISO 8601 UTC timestamp such as "2026-10-05T12:00:00Z"; the latest hourly snapshot at or before it is returned. History begins 2026-09-29. Themes with coverage.sufficient = false are returned but should not be read as meaningful. stress_index is a direction and change gauge, not a probability: read change_24h and change_7d. This is a MEASURED STATE, not a forecast. Paid route: $0.02 USDC via x402. Call list_geo_themes first (free) to see keys and coverage before paying.

Full history: https://api.protogrid.dev/v1/servers/net.qsig.x402%2Fmcp/changes

## Remotes

- https://x402.qsig.net/mcp (streamable-http, auth none, reachable true, uptime30d 0.982906)

## Packages

_none_

## Tools (5)

- `get_georisk`: QSIG geopolitical risk score (0-100, higher = more risk), with 24h
    change, 30/90-day percentile rank, regime label and event count.

    Returns the current score, or a historical one if as_of is given.
    as_of is an ISO 8601 UTC timestamp such as "2026-09-15T12:00:00Z"; the
    most recent observation at or before it is returned, with
    match_offset_seconds showing how far back the match was. History begins
    2026-09-09 and is sampled every ~15 minutes, so earlier timestamps
    return an error rather than a score.

    This is a MEASURED STATE, not a forecast. No directional or predictive
    claim is made. Paid route: $0.02 USDC via x402. Call get_track_record
    first if you want to evaluate the service before paying.
- `get_geo_themes`: QSIG geopolitical theme board. For each theme (HORMUZ_OIL, IRAN, LEVANT,
    RUSSIA_UKRAINE, CHINA_TAIWAN, FED, CRYPTO): the Polymarket crowd stress
    index and its 24h / 7d change on the same markets, tracked whale positions
    and 24h flows (aggregates only, no wallet addresses), the news-event count
    against its same-window baseline, and the top 3 markets.

    theme is an optional key; omit it for all themes. as_of is an optional
    ISO 8601 UTC timestamp such as "2026-10-05T12:00:00Z"; the latest hourly
    snapshot at or before it is returned. History begins 2026-09-29.

    Themes with coverage.sufficient = false are returned but should not be
    read as meaningful. stress_index is a direction and change gauge, not a
    probability: read change_24h and change_7d.

    This is a MEASURED STATE, not a forecast. Paid route: $0.02 USDC via x402.
    Call list_geo_themes first (free) to see keys and coverage before paying.
- `get_method`: Free. What QSIG sells - the georisk score and the geopolitical theme
    board (get_geo_themes) - what each does and does not claim, pricing,
    and the payment network.
- `get_track_record`: Free. QSIG's published validation policy: which products are live,
    what validation each carries, and which models were KILLED for failing
    the pre-registered criterion (walk-forward AUC < 0.55), with reasons.

    Use this to judge whether the paid data is worth buying.
- `list_geo_themes`: Free. Theme keys, labels, linked assets, coverage (qualifying markets,
    whale USD held, sufficient flag), method version and field notes for
    get_geo_themes. Use it to decide whether a paid call is worth making.