Seiche, LiquiLens and Undertow source data

Funding histories, bank filings and settlement data with source receipts, units and capture clocks.

我该使用它吗

质量与安全性

A
描述质量
93%
模式完整度
75%
命名质量
80%
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

~701token 数(工具定义)
~700 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.55%)

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": {
    "financial-source-data": {
      "url": "https://api.seiche.info/api/v2/research-data/mcp"
    }
  }
}

远程端点

https://api.seiche.info/api/v2/research-data/mcpstreamable-http

它能做什么

工具清单

工具(6)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢research_tracked_institutions(scope, q, limit, offset)

Search the existing Indian dossier and RBI registry populations, retaining financial-evidence gaps and source clocks. Populations overlap and are not a global census.

输入模式

{
  "type": "object",
  "properties": {
    "scope": {
      "type": "string",
      "enum": [
        "dossiers",
        "rbi_registry"
      ]
    },
    "q": {
      "type": "string",
      "maxLength": 150
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 500
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "maximum": 10000000
    }
  },
  "additionalProperties": false
}
🟢research_catalog(product)

Discover scoped funding, institution and chain-settlement datasets with coverage and rights.

输入模式

{
  "type": "object",
  "properties": {
    "product": {
      "type": "string",
      "enum": [
        "seiche",
        "liquilens",
        "undertow"
      ]
    }
  },
  "additionalProperties": false
}
🟢research_series(dataset, q, limit, offset)

Search the metric catalog and native unit definitions in a dataset.

输入模式

{
  "type": "object",
  "properties": {
    "dataset": {
      "type": "string"
    },
    "q": {
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10000
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "maximum": 10000000
    }
  },
  "required": [
    "dataset"
  ],
  "additionalProperties": false
}
🟢research_entities(dataset, q, limit, offset)

Find regulator identifiers for institutions; names are not fuzzy-joined across regimes.

输入模式

{
  "type": "object",
  "properties": {
    "dataset": {
      "type": "string"
    },
    "q": {
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10000
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "maximum": 10000000
    }
  },
  "required": [
    "dataset"
  ],
  "additionalProperties": false
}
🟢research_observations(dataset, series, entity, start, end, ...)

Read cited observations or a captured historical vintage. Earlier point-in-time availability is not assumed.

输入模式

{
  "type": "object",
  "properties": {
    "dataset": {
      "type": "string"
    },
    "series": {
      "type": "string"
    },
    "entity": {
      "type": "string"
    },
    "start": {
      "type": "string"
    },
    "end": {
      "type": "string"
    },
    "as_known_at": {
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10000
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "maximum": 10000000
    }
  },
  "required": [
    "dataset",
    "series"
  ],
  "additionalProperties": false
}
🟢research_analysis(product)

Read descriptive funding, institution concentration and settlement analysis with input references and limits.

输入模式

{
  "type": "object",
  "properties": {
    "product": {
      "type": "string",
      "enum": [
        "seiche",
        "liquilens",
        "undertow"
      ]
    }
  },
  "additionalProperties": false
}

社区

评价此服务器

证据

最近观测

已验证未记录版本6 个工具