原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚 登录

Causal Mechanism Registry

作者:adenkarabal版本 1.0.0i★ 1i在云端运行官方网站 ↗
注册名称io.github.adenkarabal/causal-mechanism-registry

安装方法

能做什么

A versioned registry of named causal mechanisms, each with definition, scope, boundary and test.

作者提供的原文

  • 连接方式 在云端运行
  • 账号或密钥 无需密钥
  • 分类 其他

为什么排在这里

此项在“连接 AI 的应用”标签中,该标签不使用星标,按以下顺序排列

1. 在 Claude 连接器目录中否
2. 团队实测过否
3. 适合泰国用户否
4. 不计星标的使用量20/100热度 0 · 新鲜度 12 · 仍在响应 8 · 用户喜欢 +0
5. 登记日期2026-11-13

用户喜欢: 0 · 最多加 5 分(每人 1 分),不能用钱买。

质量: 基础检查通过 5/5 项(仅展示,不用于排序)

安装

选择你使用的 AI 应用,然后复制设置。

用一句话让 AI 帮你安装

请帮我安装 Causal Mechanism Registry。按照 https://mcp.popnx.com/i/adenkarabal-causal-mechanism-registry.md 操作,先把命令给我看,等我同意后再运行。

粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文

通过 5/5 项检查 · 你的提问会经过开发者的服务器(adenkarabal.com) · ✓ 命令已检查 2026年11月13日

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

可连接 Claude · 约 2 分钟

不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加

  1. 打开 Claude 的 Connectors 页面

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  2. 点击“Add” → “Custom” → “Web”,填写这 2 项

    把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue

    Name · 名称Causal Mechanism Registry
    Remote MCP server URL · 地址https://adenkarabal.com/mcp

    在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add

  3. 在聊天中开启

    +ConnectorsCausal Mechanism Registry

  4. 试一试

    用 Causal Mechanism Registry 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude 说正在使用 Causal Mechanism Registry,或回答中出现 Causal Mechanism Registry 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

能否连接 ChatGPT 取决于方案

完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页

  1. 在网页版 ChatGPT 打开添加 MCP 的页面

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. 填写名称和地址

    输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin

    Name · 名称Causal Mechanism Registry
    Connection · 地址https://adenkarabal.com/mcp
  3. 在聊天中选择 Causal Mechanism Registry

    开启新聊天,输入前先从插件列表中选择 Causal Mechanism Registry

  4. 试一试

    用 Causal Mechanism Registry 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 ChatGPT 说正在使用 Causal Mechanism Registry,或回答中出现 Causal Mechanism Registry 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Claude Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  2. 粘贴这条命令并按 Enter

    claude mcp add --transport http --scope user causal-mechanism-registry https://adenkarabal.com/mcp
  3. 在 Claude Code 中输入 /mcp

    应能看到 Causal Mechanism Registry 在列表中并显示已连接

  4. 试一试

    用 Causal Mechanism Registry 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude Code 说正在使用 Causal Mechanism Registry,或回答中出现 Causal Mechanism Registry 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Cursor · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 Cursor

    在 Cursor 中打开

    Cursor 会请你确认安装,点击 Install

  2. 在 Cursor 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Causal Mechanism Registry 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Cursor 说正在使用 Causal Mechanism Registry,或回答中出现 Causal Mechanism Registry 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同

可连接 VS Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 VS Code

    在 VS Code 中打开

    VS Code 会请你确认安装,点击 Install

  2. 在 VS Code 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Causal Mechanism Registry 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 VS Code 说正在使用 Causal Mechanism Registry,或回答中出现 Causal Mechanism Registry 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

通过网页连接的应用使用的地址

地址https://adenkarabal.com/mcp

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 Causal Mechanism Registry 的人💬 讨论 →
开发者专用:终端命令和 JSON 设置

通过网页连接

Claude Code

claude mcp add --transport http --scope user causal-mechanism-registry https://adenkarabal.com/mcp

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "causal-mechanism-registry": {
      "url": "https://adenkarabal.com/mcp"
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "causal-mechanism-registry": {
      "type": "http",
      "url": "https://adenkarabal.com/mcp"
    }
  }
}

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

一览

每周下载量i
不在 npm/PyPI 上
许可证i
CC-BY-4.0
连接方式
在云端运行
传输方式
streamable-http
最新版本i
1.0.0
分类i
其他
发布到注册中心i
2026年11月13日
代码最后更新i
2026年11月13日
最近检查
2026年11月19日
作者
adenkarabal
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

通过互联网连接,适用于

ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

全部应用及其优缺点 →

它能做什么

工具名称和描述与服务器在 2026年11月19日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。

  • search_mechanisms

    Search the registry by name, identifier or a word in the definition, scope, boundary or test. Returns matching entries with id, name, layer, kind, review state, name_test and the first sentence of the definition. A term matches the start of a word, terms shorter than 2 characters

  • get_mechanism

    Read one published entry in full: definition, scope, boundary, distinguishing test, related identifiers, phase roles and status fields, with its versioned GitHub address and a citation line. Does not filter by review state; the requested identifier always returns. An unknown or r

  • resolve_name

    Turn a display name, an identifier or a retired identifier into the current identifier (for example export_pressure becomes export_earnings_shock). If nothing matches it says so and returns the closest three candidates.

  • list_mechanisms

    List entries with identifier, name, layer, kind and review state, optionally by layer and review state. The default lists every entry; with review=accepted the response states how many entries in review are not shown.

  • cite

    Return the recommended citation line for a version, its version DOI (if it has one), the DOI that covers all versions, and the licence.

  • list_versions

    List the published registry versions with release dates, version DOIs, entry counts and changes (kinds, the summary from CHANGELOG.md, the number of change items and a link to them). The first listed with default true is used when a version is not given.

  • search

    Search the registry; returns results with id, title and url. A thin wrapper over search_mechanisms for connectors that expect a search and a fetch tool. It looks in all review states and marks entries in review in the title. Entries describe processes in general, not the present

  • fetch

    Fetch one entry by identifier as text with its url and metadata. A thin wrapper over get_mechanism for connectors that expect a search and a fetch tool. Entries describe processes in general, not the present state of any country, market or asset.

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 adenkarabal 验证,该账户拥有此仓库

  • ✓ 通过

    仍在维护

    代码最后更新于7天前

  • ✓ 通过

    有许可证

    使用 CC-BY-4.0

  • ✓ 通过

    端点有响应

    在 560 毫秒内响应(HTTP 200)

  • – 不适用

    使用 OAuth 登录

    无需登录

  • ✓ 通过

    工具描述中没有隐藏指令

    已读取 8 个工具描述,未发现针对 AI 的隐藏指令

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/adenkarabal-causal-mechanism-registry.svg)](https://mcp.popnx.com/en/servers/adenkarabal-causal-mechanism-registry)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 20868 个服务器的 86%
  • 发布到注册中心的时间比此分类中其他 20868 个服务器的 87% 更新
  • 基础检查结果等于或优于此分类中其他 20868 个服务器的 99%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Causal Mechanism Registry 安全吗?

它在 5 项适用的基础检查中通过了 5 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。

它还在维护吗?

GitHub 仓库最后更新于7天前,最新版本(1.0.0)于7天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。

有什么可以替代它?

同一分类中有:World Monitor, openstatus, Oh My Posh Validator, Strata, Jitsu

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

World Monitor

Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 100 tools.

作者:koala73广泛使用★ 9.1万4天前更新

在云端运行✓ 服务方 · worldmonitor.app

openstatus

Manage monitors, status pages, incidents and maintenances in your openstatus workspace.

作者:openstatusHQ广泛使用★ 92762个月前更新

在云端运行✓ 服务方 · openstatus.dev

Strata

MCP server for progressive tool usage at any scale (see https://klavis.ai)

作者:Klavis-AI正在增长★ 582414个月前更新

在云端运行仓库已归档✓ klavis.ai

Jitsu

Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.

作者:jitsucom广泛使用★ 51364个月前更新

在云端运行✓ 服务方 · jitsu.com
与相似项目对比
本项
Causal Mechanism Registry
World MonitoropenstatusOh My Posh ValidatorStrataJitsu
运行位置在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装
需要密钥否否否否否否
可在 Claude 中按 + 添加否否否否否否
基础检查5/54/44/44/41/44/4
许可证CC-BY-4.0AGPL-3.0AGPL-3.0MITApache-2.0MIT
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Events don't repeat; processes do.

In 1930 in Chicago, Samuel Insull borrowed money to buy back the shares a rival had gathered in his electricity empire, so as not to lose control of it. He meant to protect it. Two years later the empire collapsed, and that debt was one of the links that made the structure impossible to carry in a falling market.

In the 880s in China, the Tang court gave its regional commanders more troops and more authority to put down rebellions. The force that crushed the rebellions went on to break the centre itself apart.

In Zaire, Mobutu kept his own army weak on purpose for years, out of fear of a coup. When a rebellion backed by neighbouring countries began in 1996, the army barely resisted, and the regime fell within a year.

Three continents, more than a thousand years, three decisions, and one process: a move made to keep control destroys what it was meant to protect. History books rarely put these three events side by side. We do.

What we do

We study the crises of recorded history: bank failures and famines, epidemics and wars, collapsing states and natural disasters. Our list runs from a Mesopotamian debt cancellation around 2400 BC to the Valencia flood of 2024, and it grows every week. The goal has no fixed end.

We study people: what the decision-maker knew, what they could not do, and the trap they fell into.

We study the currents that shaped history: how an idea, a faith or a wave of migration prepared the ground for events.

We study inventions: which capability made what possible.

We study the events that faded before they became crises: where the chain stopped, and why.

We study the time between crises: how the condition one disaster leaves behind prepares the next.

And we take all of them apart into the processes that drove them. We call these processes mechanisms, and the connected archive of it all the corpus.

Why shared names

The same process is described in different words in every source, and a link without a name stays invisible.

Franklin National Bank failed in New York in 1974; Silicon Valley Bank failed in California in 2023. The losses came from different places: currency trading in one, long-term bonds that lost value as rates rose in the other. The process that brought each bank down was the same. Large depositors lost confidence and pulled their money at once. Give both events the same name, and what they share and where they part become visible across nearly fifty years.

So we give every mechanism a name, a definition, a boundary and a test. The vocabulary is open and free, and it belongs to no company, so that people and AI models can talk about crises with the same names.

Chains and walls

Shared names make it possible to follow chains that are easy to miss.

In 1347 the Black Death swept across Europe. In 1377 the port of Ragusa (today's Dubrovnik) began to hold people arriving from plague areas before they could enter the city. That is how quarantine was born. In 2020, 643 years later, the world used the same tool again.

In 1994, armed groups settled in the camps in Zaire alongside the civilians fleeing the genocide in Rwanda. The armed organisation that continued in those camps prepared the ground for the Congo wars that began in 1996. The time between two crises is part of history too.

And some chains stop. In 2005 the large broker Refco went bankrupt. In its regulated futures arm, customers' assets were held apart from the firm's own accounts, so their positions were not frozen but moved quickly to another firm, and the failure did not spread through the system. Knowing where a chain stops is how we learn where it will not.

Back to today

We hold all this experience up to today's world.

The signature: a dated picture, drawn from sourced evidence, of which processes are at work now and how strongly. Strength is an editorial intensity score, not a probability.

The simulation: it takes that picture as a starting point and tries, inside a model, the question "if this condition changes, what could be set in motion?" It is an experimental thinking tool, not a forecast.

How we work

  • We show our sources openly.
  • Every check shows the number it found and never stays silent.
  • The work is reviewed by two separate families of AI models that do not see each other's findings, and an error found is corrected with its date.
  • We show what we do, where we stand and where we have not yet looked.

Concepts

CorpusThe connected archive of crises, people, currents of thought, inventions and events that faded: from financial crises to natural disasters, from wars to epidemics.
MechanismA process that drives an event and recurs in other ages.
VocabularyThe shared names of the mechanisms, each with its definition, boundary and test. Open and free.
TrapThe conditions a decision-maker is caught in: what they knew, what they could not do.
CurrentAn idea, a faith or a migration that prepares the ground for events.
InventionA capability that makes something possible.
Negative spaceEvents that faded before they became crises, and where the chain stopped.
StateThe condition a crisis leaves behind that prepares the next one.
SignatureA dated picture of which mechanisms are at work today, and how strongly.
SimulationA thinking tool that starts from the signature and tries possible chains inside a model; not a forecast.

This is a long project; it will take years. It has begun and it works, and we keep sharpening our lens with every step. Use it, correct it, support it.

[To the dashboard →](https://adenkarabal.com/pano/)


Causal Mechanism Registry

Shared names for the causal processes behind crises (economic, financial, political, social and humanitarian), each with a definition, a boundary and a test, so that people and models can name the same process in the same way.

Version 1.4.1 · 2026-11-13 · 233 entries in five layers · CC BY 4.0 · open to AI training

Mechanisms · mechanisms.json · Concepts · Principles · Agent guide · Agent skill · Seal · Changelog · Citation

One entry

Self-fulfilling run · self_fulfilling_run

Definition. Each individual's rational decision to exit encourages and accelerates others' exits until the run itself exhausts the resource.

Boundary. Exit is driven by expectations about others' exits and can strike an otherwise sound institution. Crowd action against a perceived injustice is subsistence_unrest_spiral; quiet convergence before the exit is herd_behavior.

Test. Withdrawals or hoarding accelerate because others are doing the same.

Use it

curl -s https://raw.githubusercontent.com/adenkarabal/causal-mechanism-registry/main/mechanisms.json \

| jq '.mechanisms[] | select(.id == "self_fulfilling_run")'

import json, urllib.request

reg = json.load(urllib.request.urlopen("https://raw.githubusercontent.com/adenkarabal/causal-mechanism-registry/main/mechanisms.json")) print({m["id"]: m for m in reg["mechanisms"]}"self_fulfilling_run")

Why shared names

When researchers, journalists and models describe the same crisis, they often give one process different names, or use one name for different processes. A fixed identifier with a definition, a boundary and a test lets two explanations be compared line by line, so that a disagreement is about evidence rather than about words.

The aim is a common vocabulary that belongs to no company, model or institution and that anyone can use, in the way that shared identifiers already work for software vulnerabilities (CVE) and diseases (ICD). Whether it becomes one depends on whether others use it. Institutions may propose what should be studied or added; they cannot determine definitions, boundaries, tests or findings, which are decided on evidence, not on who asks. The nature of institutional contributions is disclosed, and institutions are named only with their permission.

What this is

Events and figures show what happened. This registry names the recurring causal processes behind them, in the crises of recorded history and in today's world: for example fiscal dominance, contagion, liquidity stress or a self-fulfilling run. Each entry has a stable identifier, a definition, its scope, its boundary against neighbouring entries, and a test for when it applies.

The signature at adenkarabal.com includes 78 of these mechanisms (69 scored and 9 unknown in edition 2026-09-25); the others are named and defined but not scored in the current edition.

LayerEntriesIn the signatureWhat it holds
Core causal mechanisms13332Financial and macroeconomic channels
Social mechanisms3220Political, social and state-capacity mechanisms
Signature extensions2121Newer names in use in the signature; provisional
Corpus mechanisms420Tested in the research corpus, not yet in the signature; provisional
Crisis types55The event itself: war, famine, displacement, natural disaster, epidemic
Total23378

MECHANISMS.md has every entry in full. mechanisms.json is the same content in machine-readable form. If the two differ, mechanisms.json takes precedence.

Who it is for

Relationship to adenkarabal.com

adenkarabal.com publishes Pano, a dashboard with a dated mechanism signature and its reading, evidence coverage by country and topic, evidence cards, a synthetic model with the experimental Run tool, and Tracking, which makes the research process visible. The public dashboard does not contain the entire research corpus. This repository is the open method layer behind it: the vocabulary, the concepts needed to read it, and the principles the work is kept under.

In this repository (CC BY 4.0)On adenkarabal.com
Names, definitions, scope, boundaries and testsThe signature: the names marked in_signature, each with a 0–100 score or marked unknown, and the edition's reading of the signature
Concepts: signature, score, evidence statesEvidence coverage by country and topic (open)
Principles, the agent guide and the agent skillSource-reading titles and sourced evidence rows, except third-party text without permission to publish
A SHA-256 seal of the internal methodTracking (the state of the work), and a synthetic model with the experimental Run tool, neither of which is evidence or a forecast

The complete internal documentation of the method, as it stood on 2026-10-07, is sealed by SHA-256 digest in SEAL.md, so that it can be disclosed and checked later. What Tracking shows on adenkarabal.com does not replac

只显示了开头部分;其余内容请在仓库中阅读