Brighter

Browse, backtest and write rule-based portfolios of tokenized US stocks.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
91%
命名质量
91%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~1,354token 数(工具定义)
~938 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 1.06%)

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": {
    "brighter": {
      "url": "https://mcp.brighter.fi/mcp"
    }
  }
}

远程端点

https://mcp.brighter.fi/mcpstreamable-http

它能做什么

工具清单

工具(11)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢list_strategies(assets, beatsBenchmark, cadence, leveraged, limit, ...)

List the strategies published on brighter.fi, newest or best-performing first. Each carries its rebalance cadence, the assets it can hold, and its return over the chosen period against its benchmark. Strategies that can hold leveraged or inverse funds are excluded unless asked for.

输入模式

{
  "type": "object",
  "properties": {
    "assets": {
      "description": "Only strategies that can hold any of these tickers.",
      "items": {
        "type": "string"
      },
      "maxItems": 30,
      "type": "array"
    },
    "beatsBenchmark": {
      "description": "Only strategies ahead of their benchmark over the period.",
      "type": "boolean"
    },
    "cadence": {
      "description": "Only these rebalance cadences.",
      "items": {
        "enum": [
          "daily",
          "weekly",
          "monthly"
        ],
        "type": "string"
      },
      "maxItems": 3,
      "type": "array"
    },
    "leveraged": {
      "description": "Include strategies that can hold leveraged or inverse funds. Off by default.",
      "type": "boolean"
    },
    "limit": {
      "description": "How many to return.",
      "maximum": 24,
      "minimum": 1,
      "type": "integer"
    },
    "offset": {
      "description": "Where to start, for paging.",
      "maximum": 10000,
      "minimum": 0,
      "type": "integer"
    },
    "period": {
      "description": "Window the returns cover.",
      "enum": [
        "1y",
        "3y",
        "5y"
      ],
      "type": "string"
    },
    "sort": {
      "description": "Order of the list.",
      "enum": [
        "return",
        "newest"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}
🟢get_strategy(id)

One strategy in full: what its rule does, the parameters you can tune with their ranges and defaults, every asset it can hold, and its benchmark. Use the parameter keys with backtest_strategy.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "description": "Strategy id, as list_strategies returns it.",
      "type": "string"
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
⚪backtest_strategy(id, params, range)

Run a published strategy over real market history with parameters of your choosing. Returns its figures against its benchmark. Values outside a parameter's range are snapped into it. This is a real backtest, so make each one count.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "description": "Strategy id.",
      "type": "string"
    },
    "params": {
      "additionalProperties": {
        "type": "number"
      },
      "description": "Parameter values by key, from get_strategy. Omitted keys use their default.",
      "type": "object"
    },
    "range": {
      "description": "Backtest window. Only these are kept warm; anything else is refused.",
      "enum": [
        "1y",
        "3y",
        "5y"
      ],
      "type": "string"
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
🟢get_allocation(id, params)

What a published strategy's rule holds right now, in basis points of the portfolio. This is the live target, computed from the latest close.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "description": "Strategy id.",
      "type": "string"
    },
    "params": {
      "additionalProperties": {
        "type": "number"
      },
      "description": "Parameter values by key. Omitted keys use their default.",
      "type": "object"
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
🟢find_assets(limit, offset, query, tickers)

Search the assets a Brighter strategy can hold — tokenized US stocks, ETFs and T-bills. A rule may only name a ticker that appears here.

输入模式

{
  "type": "object",
  "properties": {
    "limit": {
      "description": "How many to return.",
      "maximum": 30,
      "minimum": 1,
      "type": "integer"
    },
    "offset": {
      "description": "Where to start.",
      "maximum": 1000,
      "minimum": 0,
      "type": "integer"
    },
    "query": {
      "description": "Match against ticker or company name.",
      "type": "string"
    },
    "tickers": {
      "description": "Look up these exact tickers.",
      "items": {
        "type": "string"
      },
      "maxItems": 30,
      "type": "array"
    }
  },
  "additionalProperties": false
}
⚪asset_history(ticker, year)

Daily closing prices for one asset over a calendar year, for checking a rule's premise against what actually happened.

输入模式

{
  "type": "object",
  "properties": {
    "ticker": {
      "description": "Asset ticker, as find_assets returns it.",
      "type": "string"
    },
    "year": {
      "description": "Calendar year.",
      "maximum": 2100,
      "minimum": 2000,
      "type": "integer"
    }
  },
  "required": [
    "ticker",
    "year"
  ],
  "additionalProperties": false
}
🟡dsl_reference(indicators, limits)

How to write a Brighter strategy: the language's blocks, indentation rules, indicators and limits. Read this before writing any rule — the language is small and specific, and guessing its syntax wastes a turn.

输入模式

{
  "type": "object",
  "properties": {
    "indicators": {
      "description": "Include the full indicator table with every measure's syntax. Off by default; the reference already names them.",
      "type": "boolean"
    },
    "limits": {
      "description": "Include the numeric limits a rule must stay inside.",
      "type": "boolean"
    }
  },
  "additionalProperties": false
}
🟡strategy_schema

The JSON schema for a strategy as an object, for when you would rather build the rule tree than write the text. check_strategy and backtest_code both accept text, which is usually easier.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢check_strategy(code)

Check a strategy written in Brighter's language: syntax, semantics, and whether every ticker it names is one Brighter can actually trade. Returns the faults with their line and column. Costs nothing and calls nothing upstream — check before you backtest.

输入模式

{
  "type": "object",
  "properties": {
    "code": {
      "description": "The strategy, in Brighter's language.",
      "type": "string"
    }
  },
  "required": [
    "code"
  ],
  "additionalProperties": false
}
⚪format_strategy(code)

Rewrite a strategy in the language's canonical form — the spelling Studio's editor shows. Useful for checking that what you wrote means what you think it means.

输入模式

{
  "type": "object",
  "properties": {
    "code": {
      "description": "The strategy, in Brighter's language.",
      "type": "string"
    }
  },
  "required": [
    "code"
  ],
  "additionalProperties": false
}
🟢backtest_code(code, range)

Run a strategy you have written against real market history and return its figures. This is a real backtest against real prices — not a simulation and not cached per call — so run it deliberately, after check_strategy passes. Returns metrics only, never the curve.

输入模式

{
  "type": "object",
  "properties": {
    "code": {
      "description": "The strategy, in Brighter's language.",
      "type": "string"
    },
    "range": {
      "description": "Window to test over.",
      "enum": [
        "1y",
        "3y",
        "5y"
      ],
      "type": "string"
    }
  },
  "required": [
    "code"
  ],
  "additionalProperties": false
}

社区

评价此服务器

证据

最近观测

已验证未记录版本11 个工具