Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words Sign in

Causal Mechanism Registry

by adenkarabalversion 1.0.0i★ 1iRuns in the cloudOfficial site ↗
Registry nameio.github.adenkarabal/causal-mechanism-registry

How to install

What it does

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

  • Connects Runs in the cloud
  • Account or key No key needed
  • Category Other

Why it ranks here

This one is in the “Apps that connect to AI” tab, which is ordered without stars, in this order

1. In Claude’s connector directoryNo
2. Tried by our teamNo
3. Works for Thai usersNo
4. Usage without stars20/100Popularity 0 · Freshness 12 · Still answering 8 · Likes from users +0
5. Listed on2026-11-13

Likes from users: 0 · Adds at most 5 points to the order (1 per person). It cannot be bought.

Quality: Passed 5/5 basic checks (shown, not used for ordering)

Install

Pick the AI app you use, then copy the settings.

Let your AI install it with one sentence

Please install Causal Mechanism Registry. Follow https://mcp.popnx.com/i/adenkarabal-causal-mechanism-registry.md, show me the commands and wait for my OK before running them.

Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads

Passed 5/5 checks · What you ask goes through the maker’s server (adenkarabal.com) · ✓ Commands checked Nov 13, 2026

First: which AI do you use?

Pick your app and the steps appear below.

Works with Claude · about 2 min

No key, nothing to install · Set it up once on claude.ai or the desktop app, then use it in chat · free accounts can add 1 · on Team/Enterprise an Owner adds it

  1. Open Claude’s Connectors page

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  2. Click “Add” → “Custom” → “Web” and fill in these 2 fields

    Copy each value into the field with the same name in Claude, then click Continue

    Name · NameCausal Mechanism Registry
    Remote MCP server URL · Addresshttps://adenkarabal.com/mcp

    Click Continue past the sign-in settings Claude detected · under Authentication choose what the maker says (Sign in now, Sign in when needed or No sign in), then click Add

  3. Turn it on in a chat

    +ConnectorsCausal Mechanism Registry

  4. Try it

    Use Causal Mechanism Registry and tell me what you can do for me, then show me one thing

    ✓ If Claude says it is using Causal Mechanism Registry or shows a Causal Mechanism Registry tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with ChatGPT, depending on your plan

Full MCP: ChatGPT Business, Enterprise or Edu on the web · Pro: connects with read/fetch permissions, so tools that change data may not work · Plus: not confirmed in OpenAI’s docs; if you see an add-custom-MCP option on the Plugins page you can try these steps · web only

  1. Open ChatGPT’s add-MCP page on the web

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. Fill in the name and address

    Enter a name, paste the address under Connection, tick the risk warning and click Create as a plugin

    Name · NameCausal Mechanism Registry
    Connection · Addresshttps://adenkarabal.com/mcp
  3. Pick Causal Mechanism Registry in a chat

    Start a new chat and pick Causal Mechanism Registry from your plugins before typing

  4. Try it

    Use Causal Mechanism Registry and tell me what you can do for me, then show me one thing

    ✓ If ChatGPT says it is using Causal Mechanism Registry or shows a Causal Mechanism Registry tool in the answer, you are connected

Menu names checked against OpenAI’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with Claude Code · about 2 min

No key, nothing to install

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: open PowerShell

  2. Paste this command and press Enter

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

    You should see Causal Mechanism Registry listed as connected

  4. Try it

    Use Causal Mechanism Registry and tell me what you can do for me, then show me one thing

    ✓ If Claude Code says it is using Causal Mechanism Registry or shows a Causal Mechanism Registry tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with Cursor · about 2 min

No key, nothing to install

  1. Click this button to open Cursor

    Open in Cursor

    Cursor asks you to confirm; click Install

  2. Open the AI chat in Cursor in Agent mode

  3. Try it

    Use Causal Mechanism Registry and tell me what you can do for me, then show me one thing

    ✓ If Cursor says it is using Causal Mechanism Registry or shows a Causal Mechanism Registry tool in the answer, you are connected

Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with VS Code · about 2 min

No key, nothing to install

  1. Click this button to open VS Code

    Open in VS Code

    VS Code asks you to confirm; click Install

  2. Open the AI chat in VS Code in Agent mode

  3. Try it

    Use Causal Mechanism Registry and tell me what you can do for me, then show me one thing

    ✓ If VS Code says it is using Causal Mechanism Registry or shows a Causal Mechanism Registry tool in the answer, you are connected

Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.

See every app that uses MCP →

Address for apps that connect over the web

Addresshttps://adenkarabal.com/mcp

JSON settings are under “For developers” below

Stuck? Ask people who use Causal Mechanism Registry💬 Discussion →
For developers: Terminal commands and JSON settings

Over the web

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"
    }
  }
}

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

At a glance

Downloads per weeki
Not on npm/PyPI
Licencei
CC-BY-4.0
Connection
Runs in the cloud
Transport
streamable-http
Latest versioni
1.0.0
Categoryi
Other
Published to registryi
Nov 13, 2026
Code last changedi
Nov 13, 2026
Last checked
Nov 19, 2026
Maker
adenkarabal
Registry status
Active

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Connect over the internet in

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

All apps, with pros and cons →

Related guides

What it can do

Tool names and descriptions exactly as the server reported them on Nov 19, 2026. The maker wrote them, not us; we show them as plain text.

  • 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.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 20, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account adenkarabal, which owns the repo

  • ✓ Pass

    Still maintained

    Code last changed 7 days ago

  • ✓ Pass

    Has a licence

    Uses CC-BY-4.0

  • ✓ Pass

    Endpoint responds

    Responded in 560 ms (HTTP 200)

  • – Not applicable

    Sign-in with OAuth

    No sign-in needed

  • ✓ Pass

    No hidden instructions in tool descriptions

    Read 8 tool descriptions and found no hidden instructions to the AI

What we check → · JSON

Makers: ask for a re-check or report wrong info
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

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

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

User reviews

No reviews yet

Sign in to write a review

Compared with others in Otheri

  • More stars than 86% of the other 20868 servers in this category
  • Published to the registry more recently than 87% of the other 20868 servers in this category
  • Basic checks equal to or better than 99% of the other 20868 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Causal Mechanism Registry safe?

It passed 5 of 5 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.

Is it still maintained?

The GitHub repo last changed 7 days ago, and the latest version (1.0.0) reached the registry 7 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT on the web (full MCP on Business and above; Pro read-only).

What can I use instead?

In the same category: World Monitor, openstatus, Oh My Posh Validator, Strata, Jitsu

Similar alternatives

Same category, other makers, commands already checked. Official ones first, then by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

World Monitor

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

by koala73Widely used★ 90.9KUpdated 4 days ago

Runs in the cloud✓ service owner · worldmonitor.app

openstatus

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

by openstatusHQWidely used★ 9.3KUpdated 2 months ago

Runs in the cloud✓ service owner · openstatus.dev

Oh My Posh Validator

Validate oh-my-posh configurations and segment snippets against the official schema.

by JanDeDobbeleerWidely used★ 23.8K Stars for the whole repoUpdated 31 days ago

Runs in the cloud✓ service owner · ohmyposh.dev

Strata

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

by Klavis-AIGrowing★ 5.8KUpdated 14 months ago

Runs in the cloudRepo archived✓ klavis.ai

Jitsu

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

by jitsucomWidely used★ 5.1KUpdated 4 months ago

Runs in the cloud✓ service owner · jitsu.com
Compared with similar ones
This one
Causal Mechanism Registry
World MonitoropenstatusOh My Posh ValidatorStrataJitsu
Runs whereRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to install
Needs a keyNoNoNoNoNoNo
Add with + in ClaudeNoNoNoNoNoNo
Basic checks5/54/44/44/41/44/4
LicenseCC-BY-4.0AGPL-3.0AGPL-3.0MITApache-2.0MIT
PriceNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registry

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

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

Only the beginning is shown; read the rest in the repo