Independent AI model test scores on 5 tasks: inbox, scheduling, receipts, finance, support replies.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Headline scores for every model RealRun tested on a task, best first, with cost tier and the metric definition.
Task id, e.g. 'receipts'. See list_tasks.
Headline scores for every model RealRun tested on a task, best first, with cost tier and the metric definition.
| Argument | Type | Description |
|---|---|---|
| task* | string | Task id, e.g. 'receipts'. See list_tasks. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"task"
],
"properties": {
"task": {
"enum": [
"inbox-triage",
"meeting-scheduling",
"receipts",
"finance",
"support-replies"
],
"type": "string",
"description": "Task id, e.g. 'receipts'. See list_tasks."
}
}
}Models RealRun flagged as not recommended or needing caution on a task (scam failures, invented data, inconsistency).
| Argument | Type | Description |
|---|---|---|
| task* | string | Task id, e.g. 'receipts'. See list_tasks. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"task"
],
"properties": {
"task": {
"enum": [
"inbox-triage",
"meeting-scheduling",
"receipts",
"finance",
"support-replies"
],
"type": "string",
"description": "Task id, e.g. 'receipts'. See list_tasks."
}
}
}List the everyday tasks RealRun has tested AI models on, with item counts, test dates, results pages and playbook prices.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Recommend which AI model to use for a task given a priority: 'accuracy', 'cost' or 'balanced'. Never recommends models RealRun flagged as not recommended.
| Argument | Type | Description |
|---|---|---|
| task* | string | Task id, e.g. 'receipts'. See list_tasks. |
| priority | string | What matters most. |
| include_subscription | boolean | Include Claude models (tested on a subscription, no metered cost). |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"task"
],
"properties": {
"task": {
"enum": [
"inbox-triage",
"meeting-scheduling",
"receipts",
"finance",
"support-replies"
],
"type": "string",
"description": "Task id, e.g. 'receipts'. See list_tasks."
},
"priority": {
"enum": [
"accuracy",
"cost",
"balanced"
],
"type": "string",
"default": "balanced",
"description": "What matters most."
},
"include_subscription": {
"type": "boolean",
"default": true,
"description": "Include Claude models (tested on a subscription, no metered cost)."
}
}
}