# WIA360: AI session probe and match

> Probe an AI session with WIA360 missions and match it to a human WIA360 KYEOL profile.

- name: com.wiaacademy/wia360
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 89/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.wiaacademy%2Fwia360
- tools: https://api.protogrid.dev/v1/servers/com.wiaacademy%2Fwia360/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "wia360": {
      "type": "http",
      "url": "https://wia360-mcp.wiaacademy.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-3d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 89/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 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: 100 (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
- pass `tools.annotations`: 3 of 3 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,147 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

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

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 3 of the 7 days needed

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

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

- tools: 3, about 1,147 tokens to load them all
- tool set hash: b94daf1a5faf7ac0f84c2d12200ce1e7
- tools last changed: 2026-10-17T19:35:32.697Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.wiaacademy/wia360.svg)](https://protogrid.dev/servers/com.wiaacademy/wia360)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-17 `get_match` changed (annotations)
- 2026-10-17 `score_session` changed (annotations)
- 2026-10-17 `run_probe` changed (annotations)

Full history: https://api.protogrid.dev/v1/servers/com.wiaacademy%2Fwia360/changes

## Remotes

- https://wia360-mcp.wiaacademy.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (3)

- `get_match`: Compute the compatibility match between a human WIA360 KYEOL profile and the AI session profile built up via score_session calls under the same session_ref. Human axis values come from the human's WIA360 Quick or full assessment result (initiative/verification/pivot/adventure raw scores). Without paid=true, only matched_axis_count/available_axis_count are returned (free teaser) — pass paid=true only when the human has an active paid WIA360 profile, to reveal score/grade/heatmap/priming prompts.
- `run_probe`: Get the next WIA360 session-probe mission for a given session_ref (auto-generate a new random session_ref string yourself the first time you call this for a session, then reuse it for every subsequent run_probe/score_session/get_match call in that same run). Missions arrive in random order and already exclude probes already finalized for this session_ref. Returns {done:true} when all 6 are finished. IMPORTANT — deliver wrapped_mission verbatim to the target AI session you are evaluating (paste it as a normal task, not as a quoted "here is a test" framing) and bring its raw reply back for score_session. Some probes (P4) are two-turn: send wrapped_mission first, wait for the reply, then send turn2_wrapped_mission and use ONLY that second reply for scoring. Pick lang based on the language the target AI session actually converses in — not your own output language for this tool call — since the mission text and score_session scoring keys must match.
- `score_session`: Submit the target AI session's raw reply text to a probe mission (from run_probe) for rule-based scoring. If the verdict is "invalid" or "omitted_pending", call run_probe again with the SAME session_ref to get a fresh variant of the same probe and retry once (pass the returned attempt_id back as retry_of) — after a second failure just move on, it is recorded as-is. IMPORTANT — lang must match the lang that was passed to the run_probe call that produced this mission; scoring uses a language-specific keyword dictionary and silently misfires if lang doesn't match how the mission was worded.