Search / io.github.shrek9999/atena
protogridR0· no sign-inDecision support for AI fitness agents: next-action choices under uncertainty and trade-offs.
v1.2.0 · active · repository · website · descriptor JSON · versions
{
"mcpServers": {
"atena": {
"type": "http",
"url": "https://atena-mcp.onrender.com/mcp"
}
}
}claude mcp add --transport http atena https://atena-mcp.onrender.com/mcp[mcp_servers.atena]
url = "https://atena-mcp.onrender.com/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"atena": {
"type": "remote",
"url": "https://atena-mcp.onrender.com/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"atena": {
"type": "http",
"url": "https://atena-mcp.onrender.com/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=atena&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXRlbmEtbWNwLm9ucmVuZGVyLmNvbS9tY3AifQ%3D%3D"
}{
"servers": {
"atena": {
"type": "http",
"url": "https://atena-mcp.onrender.com/mcp"
}
}
}{
"mcpServers": {
"atena": {
"httpUrl": "https://atena-mcp.onrender.com/mcp"
}
}
}extensions:
"atena":
enabled: true
name: "atena"
type: streamable_http
uri: "https://atena-mcp.onrender.com/mcp"
timeout: 300
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28protocol.statelessonly applies to 2026-07-28 serversprotocol.transportstreamable HTTPprotocol.list_ttlonly applies to 2026-07-28 serversauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_lengthdescriptions are concisetools.schemasevery tool has an object input schematools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky onestools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: atena_capabilities (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); atena_decide (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)tools.token_costabout 548 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changes2 tool changes in 30 daysstability.rug_pullno tool changed its meaning under the same namedeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packageatena_capabilitieschangeddescriptionReturn ATENA capabilities and supported decision types.
Return ATENA capabilities, supported decision types, endpoints and agent-use guidance.
atena_decidechangeddescriptionUse 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.
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: list_changes · trend: quality JSON.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+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. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://atena-mcp.onrender.com/mcp streamable-http | none | yes | 98% | 345 ms | 2025-11-25 | 2026-10-20 |
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. |
Schemas: list_tools.
{
"name": "io.github.shrek9999/atena",
"title": "ATENA Decision Intelligence",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://atena-mcp.onrender.com/mcp",
"type": "streamable-http"
}
],
"version": "1.2.0",
"repository": {
"url": "https://github.com/shrek9999/atena-mvp",
"source": "github"
},
"websiteUrl": "https://github.com/shrek9999/atena-mvp",
"description": "Decision support for AI fitness agents: next-action choices under uncertainty and trade-offs."
}