Estimate hours and cost of systematic or literature reviews: screening and full-text reading.
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.
Calculates the hours spent screening titles and abstracts and reading full texts, per review and per year, the share of each stage, the extra effort of double screening and, when an hourly cost is given, the yearly cost in Brazilian reais.
Kind of review.
Records returned by the database search of one review.
Full texts read per review.
Reviews the group runs per year.
How many people screen each record.
Minutes to read and extract one full text.
Minutes to screen one title and abstract.
Optional cost of one hour of work, in BRL.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http review-time https://tools.realmarketlabs.com/mcp/review-time
Calculates the hours spent screening titles and abstracts and reading full texts, per review and per year, the share of each stage, the extra effort of double screening and, when an hourly cost is given, the yearly cost in Brazilian reais.
| Argument | Type | Description |
|---|---|---|
| review_type* | string | Kind of review. |
| records_found* | integer | Records returned by the database search of one review. |
| full_texts_read* | integer | Full texts read per review. |
| hourly_cost_brl | number | Optional cost of one hour of work, in BRL. |
| reviews_per_year* | integer | Reviews the group runs per year. |
| reviewers_per_record* | string | How many people screen each record. |
| minutes_per_full_text* | number | Minutes to read and extract one full text. |
| minutes_per_record_screening* | number | Minutes to screen one title and abstract. |
{
"type": "object",
"required": [
"review_type",
"reviews_per_year",
"records_found",
"minutes_per_record_screening",
"full_texts_read",
"minutes_per_full_text",
"reviewers_per_record"
],
"properties": {
"review_type": {
"enum": [
"systematic",
"integrative_or_scoping",
"narrative"
],
"type": "string",
"description": "Kind of review."
},
"records_found": {
"type": "integer",
"maximum": 500000,
"minimum": 1,
"description": "Records returned by the database search of one review."
},
"full_texts_read": {
"type": "integer",
"maximum": 20000,
"minimum": 0,
"description": "Full texts read per review."
},
"hourly_cost_brl": {
"type": "number",
"maximum": 5000,
"minimum": 0,
"description": "Optional cost of one hour of work, in BRL."
},
"reviews_per_year": {
"type": "integer",
"maximum": 500,
"minimum": 1,
"description": "Reviews the group runs per year."
},
"reviewers_per_record": {
"enum": [
"one",
"two",
"three_or_more"
],
"type": "string",
"description": "How many people screen each record."
},
"minutes_per_full_text": {
"type": "number",
"maximum": 1000,
"minimum": 1,
"description": "Minutes to read and extract one full text."
},
"minutes_per_record_screening": {
"type": "number",
"maximum": 60,
"minimum": 0.1,
"description": "Minutes to screen one title and abstract."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 4, 2026.