RealRun
Independent test scores for AI models on everyday tasks: inbox, scheduling, receipts.
Sollte ich dies verwenden
Qualität und Sicherheit
Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.
Kontextkosten
Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.
Installieren
Installation mit einem Klick
Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:
{
"mcpServers": {
"realrun": {
"url": "https://realrun.baseledgerip.com/mcp"
}
}
}Remote-Endpunkte
https://realrun.baseledgerip.com/mcpstreamable-httpWas es kann
Tool-Inventar
Tools (4)
🟢list_tasks
List the everyday tasks RealRun has tested AI models on, with item counts, test dates, results pages and playbook prices.
Eingabe-Schema
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_scores(task)
Headline scores for every model RealRun tested on a task, best first, with cost tier and the metric definition.
Eingabe-Schema
{
"type": "object",
"properties": {
"task": {
"type": "string",
"enum": [
"inbox-triage",
"meeting-scheduling",
"receipts",
"finance",
"support-replies"
],
"description": "Task id, e.g. 'receipts'. See list_tasks."
}
},
"required": [
"task"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢recommend_model(task, priority, include_subscription)
Recommend which AI model to use for a task given a priority: 'accuracy', 'cost' or 'balanced'. Never recommends models RealRun flagged as not recommended.
Eingabe-Schema
{
"type": "object",
"properties": {
"task": {
"type": "string",
"enum": [
"inbox-triage",
"meeting-scheduling",
"receipts",
"finance",
"support-replies"
],
"description": "Task id, e.g. 'receipts'. See list_tasks."
},
"priority": {
"default": "balanced",
"description": "What matters most.",
"type": "string",
"enum": [
"accuracy",
"cost",
"balanced"
]
},
"include_subscription": {
"default": true,
"description": "Include Claude models (tested on a subscription, no metered cost).",
"type": "boolean"
}
},
"required": [
"task"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_warnings(task)
Models RealRun flagged as not recommended or needing caution on a task (scam failures, invented data, inconsistency).
Eingabe-Schema
{
"type": "object",
"properties": {
"task": {
"type": "string",
"enum": [
"inbox-triage",
"meeting-scheduling",
"receipts",
"finance",
"support-replies"
],
"description": "Task id, e.g. 'receipts'. See list_tasks."
}
},
"required": [
"task"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}Community
Nachweis