RealRun
Independent test scores for AI models on everyday tasks: inbox, scheduling, receipts.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"realrun": {
"url": "https://realrun.baseledgerip.com/mcp"
}
}
}Remote endpoints
https://realrun.baseledgerip.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (4)
🟢list_tasks
List the everyday tasks RealRun has tested AI models on, with item counts, test dates, results pages and playbook prices.
Input Schema
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_scores(task)
Headline scores for every model RealRun tested on a task, best first, with cost tier and the metric definition.
Input Schema
{
"type": "object",
"properties": {
"task": {
"type": "string",
"enum": [
"inbox-triage",
"meeting-scheduling",
"receipts",
"finance",
"support-replies"
],
"description": "Task id, e.g. 'receipts'. See list_tasks."
}
},
"required": [
"task"
],
"$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.
Input 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"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_warnings(task)
Models RealRun flagged as not recommended or needing caution on a task (scam failures, invented data, inconsistency).
Input Schema
{
"type": "object",
"properties": {
"task": {
"type": "string",
"enum": [
"inbox-triage",
"meeting-scheduling",
"receipts",
"finance",
"support-replies"
],
"description": "Task id, e.g. 'receipts'. See list_tasks."
}
},
"required": [
"task"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}Community
Evidence