# ATENA Decision Intelligence

> Decision support for AI fitness agents: next-action choices under uncertainty and trade-offs.

- name: io.github.shrek9999/atena
- version: 1.2.0
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.shrek9999%2Fatena
- tools: https://api.protogrid.dev/v1/servers/io.github.shrek9999%2Fatena/tools

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

## Connection (mcpServers)

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


## Trust

- hygiene: 100
- liveness: 99
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-98% +updated-6d-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 2025-11-25; 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: 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: atena_decide (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); atena_capabilities (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 548 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`: 2 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: 2, about 548 tokens to load them all
- tool set hash: f34abe3b3b087995b16440b14e47cc92
- tools last changed: 2026-10-07T15:50:50.486Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.shrek9999/atena.svg)](https://protogrid.dev/servers/io.github.shrek9999/atena)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-07 `atena_capabilities` changed (description)
  - before: Return ATENA capabilities and supported decision types.
  - after: Return ATENA capabilities, supported decision types, endpoints and agent-use guidance.
- 2026-10-07 `atena_decide` changed (description)
  - before: Use ATENA when an AI agent needs a defensible next training/human-performance decision rather than a generic answer. Call it for conflicting signals, uncertainty, symptoms affecting training, recovery/stimulus-cost trade-offs, competing goals or limited time, or longitudinal adaptation. ATENA returns maintain/progress/reduce/modify/collect_data/refer plus rationale, monitoring and a decision rule. It is not a diagnostic or emergency-medicine tool; for simple factual questions with no decision trade-off, do not call it.
  - after: Decision-control specialist for AI fitness and human-performance agents. Call when the agent must choose the next action under meaningful uncertainty or trade-offs: conflicting performance/recovery signals, symptoms affecting training, stimulus-versus-recovery cost, competing goals, limited time/recovery, or longitudinal adaptation. Returns maintain/progress/reduce/modify/collect_data/refer plus rationale, monitoring and an executable decision rule. Not a diagnostic or emergency-medicine tool. Do not call for simple factual questions with no decision trade-off.

Full history: https://api.protogrid.dev/v1/servers/io.github.shrek9999%2Fatena/changes

## Remotes

- https://atena-mcp.onrender.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9811321)

## Packages

_none_

## Tools (2)

- `atena_capabilities`: Return ATENA capabilities, supported decision types, endpoints and agent-use guidance.
- `atena_decide`: Decision-control specialist for AI fitness and human-performance agents.

Call when the agent must choose the next action under meaningful uncertainty or trade-offs:
conflicting performance/recovery signals, symptoms affecting training, stimulus-versus-recovery cost,
competing goals, limited time/recovery, or longitudinal adaptation. Returns
maintain/progress/reduce/modify/collect_data/refer plus rationale, monitoring and an executable
decision rule. Not a diagnostic or emergency-medicine tool. Do not call for simple factual questions
with no decision trade-off.