prefrosh.ai
College admissions: admit rates by round, your odds, compare colleges, and a mock admissions game.
我该使用它吗
质量与安全性
发现（1）
- LOWTool 'game_vote' description lacks action verb在 game_vote 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"prefrosh": {
"url": "https://prefrosh.ai/mcp"
}
}
}远程端点
https://prefrosh.ai/mcpstreamable-http它能做什么
工具清单
工具（8）
🟢school_card(school)
Show one college as a card: photo or campus map, overall admit rate and admit rate by round (Early Decision, Early Action, Regular Decision) with deadlines, SAT/ACT middle 50%, testing policy, sticker cost, average net price, graduation rate, biggest majors, and a link to its prefrosh.ai page. Use for "tell me about X", "how hard is it to get into X", "what are X's deadlines". Data is from the school's Common Data Set and federal data; cite the prefrosh.ai URL in the result.
输入模式
{
"type": "object",
"properties": {
"school": {
"type": "string",
"description": "College name as the user wrote it, e.g. \"Tufts\", \"UNC\", \"Wash U\"."
}
},
"required": [
"school"
],
"additionalProperties": false
}🟢my_odds(schools, gpa, sat, act, class_rank, ...)
Estimate a student's admission odds at one or more colleges, by round, with a likely range, from GPA and test scores (plus optional class rank, home state, legacy, first-generation, aid). Same model as prefrosh.ai/chance. Always tell the user this is an estimate from grades and scores only; essays, activities and recommendations can move it a lot. Needs at least a GPA or a test score; ask for them if missing rather than guessing.
输入模式
{
"type": "object",
"properties": {
"schools": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"maxItems": 12,
"description": "College names."
},
"gpa": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "Unweighted GPA, ideally on a 4.0 scale (a 100-point average also works)."
},
"sat": {
"type": "integer",
"minimum": 400,
"maximum": 1600,
"description": "Best total SAT (superscore is fine)."
},
"act": {
"type": "integer",
"minimum": 1,
"maximum": 36,
"description": "Best ACT composite."
},
"class_rank": {
"type": "string",
"enum": [
"top5",
"top10",
"top25",
"top50",
"below"
],
"description": "Class rank bucket, if known (percent of class)."
},
"home_state": {
"type": "string",
"description": "Two-letter US state the student lives in (matters for public universities)."
},
"legacy": {
"type": "boolean",
"description": "A parent attended this college."
},
"first_gen": {
"type": "boolean",
"description": "First in family to attend a four-year college."
},
"needs_aid": {
"type": "boolean",
"description": "Will apply for need-based aid (default true)."
}
},
"required": [
"schools"
],
"additionalProperties": false
}🟢compare(schools, gpa, sat, act, home_state)
Compare 2 to 4 colleges side by side: admit rates by round, SAT/ACT ranges, testing policy, sticker cost, average net price, graduation rate, size and setting. If GPA or scores are given, adds the student's estimated odds (same model as prefrosh.ai/chance).
输入模式
{
"type": "object",
"properties": {
"schools": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 2,
"maxItems": 4
},
"gpa": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "Unweighted GPA, ideally on a 4.0 scale (a 100-point average also works)."
},
"sat": {
"type": "integer",
"minimum": 400,
"maximum": 1600,
"description": "Best total SAT (superscore is fine)."
},
"act": {
"type": "integer",
"minimum": 1,
"maximum": 36,
"description": "Best ACT composite."
},
"home_state": {
"type": "string",
"description": "Two-letter US state the student lives in (matters for public universities)."
}
},
"required": [
"schools"
],
"additionalProperties": false
}🟢admissions_game(school, round, application, major, visited_campus)
Run the student's application past prefrosh.ai's simulated admissions committee for one college and round: five fictional readers (first, second, essay and faculty readers, and a dean who chairs) read it, argue, vote (accept / waitlist or defer / deny), and give the top 3 fixes. It is a simulation, not a prediction. Takes about a minute; the room plays out in the view. Pass the student's own application text exactly as they gave it (essays, activities, grades, scores) in "application"; never write, invent or improve content for them. If they have not shared their application, ask them to paste it first.
输入模式
{
"type": "object",
"properties": {
"school": {
"type": "string",
"description": "College name."
},
"round": {
"type": "string",
"enum": [
"ED",
"EDII",
"EA",
"REA",
"RD"
],
"description": "Application round. Default RD."
},
"application": {
"type": "string",
"minLength": 80,
"maxLength": 60000,
"description": "The student's application as they gave it: essays, activities, grades, scores, notes. Verbatim."
},
"major": {
"type": "string",
"description": "Intended major, if stated."
},
"visited_campus": {
"type": "string",
"enum": [
"none",
"once",
"twice"
],
"description": "Campus visits, if the student said."
}
},
"required": [
"school",
"application"
],
"additionalProperties": false
}🟢game_read(kind, school, round, application, major, ...)
App-only. One reader of the admissions game reads the file.
输入模式
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"first",
"second",
"essay",
"faculty"
]
},
"school": {
"type": "string"
},
"round": {
"type": "string"
},
"application": {
"type": "string",
"maxLength": 60000
},
"major": {
"type": "string"
},
"visits": {
"type": "string"
},
"run": {
"type": "object"
}
},
"required": [
"kind",
"school",
"application",
"run"
]
}🟢game_vote(readers, school, round, application, major, ...)
App-only. The committee meets and votes.
输入模式
{
"type": "object",
"properties": {
"readers": {
"type": "object"
},
"school": {
"type": "string"
},
"round": {
"type": "string"
},
"application": {
"type": "string",
"maxLength": 60000
},
"major": {
"type": "string"
},
"visits": {
"type": "string"
},
"run": {
"type": "object"
}
},
"required": [
"school",
"application",
"run",
"readers"
]
}🟢game_debrief(readers, school, round, application, major, ...)
App-only. The chair writes the debrief.
输入模式
{
"type": "object",
"properties": {
"readers": {
"type": "object"
},
"school": {
"type": "string"
},
"round": {
"type": "string"
},
"application": {
"type": "string",
"maxLength": 60000
},
"major": {
"type": "string"
},
"visits": {
"type": "string"
},
"run": {
"type": "object"
}
},
"required": [
"school",
"application",
"run",
"readers"
]
}🟢game_done(school, usage, seconds)
App-only. Records that a run finished (counts only).
输入模式
{
"type": "object",
"properties": {
"school": {
"type": "string"
},
"usage": {
"type": "object"
},
"seconds": {
"type": "number"
}
}
}社区
证据