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

DAG Studio WebMCP

by Black-Swan-Causal-Labsversion 1.0.0i★ 0iRuns in the cloudOfficial site ↗
Registry nameio.github.Black-Swan-Causal-Labs/dag-studio-webmcp

How to install

What it does

Read and edit a live DAG Studio canvas through its predefined WebMCP tools.

  • Connects Runs in the cloud
  • Account or key Needs Authorization
  • Category Other

Why it ranks here

Lists are ordered by a usage score (out of 100) built from these parts

Popularity0/80GitHub stars or weekly downloads: the larger counts 60, the smaller 20
Freshness12/12Full marks for a release or code change within 30 days
Still answering8/8The cloud endpoint answered at the last check
Usage score20/100

Quality: Passed 5/5 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)

Install

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

Let your AI install it with one sentence

Please install DAG Studio WebMCP. Follow https://mcp.popnx.com/i/black-swan-causal-labs-dag-studio-webmcp.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 (dag-studio-webmcp-bridge.jdiazdecaro.workers.dev) · ✓ Commands checked Nov 13, 2026

First: which AI do you use?

Pick your app and the steps appear below.

Works with Claude · about 5 min

You need a DAG Studio WebMCP key (create it on the maker’s site) · 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. Sign up and create a DAG Studio WebMCP key

    Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.

    Open the DAG Studio WebMCP site ↗

  2. Open Claude’s Connectors page

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  3. 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 · NameDAG Studio WebMCP
    Remote MCP server URL · Addresshttps://dag-studio-webmcp-bridge.jdiazdecaro.workers.dev/mcp

    Under Request headers, add this name and value

    Header nameAuthorization
    ValueBearer <paste your key here>

    Paste the key only into the app’s field, never into a chat or to anyone

    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

  4. Turn it on in a chat

    +ConnectorsDAG Studio WebMCP

  5. Try it

    Use DAG Studio WebMCP and tell me what you can do for me, then show me one thing

    ✓ If Claude says it is using DAG Studio WebMCP or shows a DAG Studio WebMCP 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

ChatGPT cannot connect DAG Studio WebMCP yet

DAG Studio WebMCP needs your own key to connect, but OpenAI’s help page only describes OAuth sign-in; there is no key option we could verify

What you can do instead

A · Use an app that can connect DAG Studio WebMCP

  • You need a DAG Studio WebMCP key (create it on the maker’s site) · 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
  • You need a DAG Studio WebMCP key (create it on the maker’s site)
  • You need a DAG Studio WebMCP key (create it on the maker’s site)
  • You need a DAG Studio WebMCP key (create it on the maker’s site)

B · Others in Other that work with ChatGPT

Picked from the most used in the same category, only ones that connect by address with no key

Works with Claude Code · about 5 min

You need a DAG Studio WebMCP key (create it on the maker’s site)

  1. Sign up and create a DAG Studio WebMCP key

    Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.

    Open the DAG Studio WebMCP site ↗

  2. Open Terminal

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

  3. Paste this command and press Enter

    claude mcp add --transport http --scope user dag-studio-webmcp https://dag-studio-webmcp-bridge.jdiazdecaro.workers.dev/mcp --header 'Authorization: Bearer your-value'

    Replace “your-value” with your key before pressing Enter

    Paste the key only into the app’s field, never into a chat or to anyone

  4. Type /mcp in Claude Code

    You should see DAG Studio WebMCP listed as connected

  5. Try it

    Use DAG Studio WebMCP and tell me what you can do for me, then show me one thing

    ✓ If Claude Code says it is using DAG Studio WebMCP or shows a DAG Studio WebMCP 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 5 min

You need a DAG Studio WebMCP key (create it on the maker’s site)

  1. Sign up and create a DAG Studio WebMCP key

    Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.

    Open the DAG Studio WebMCP site ↗

  2. Click this button to open Cursor

    Open in Cursor

    Cursor asks you to confirm; click Install

  3. Fill in your key

    In the DAG Studio WebMCP settings, Authorization is empty; add your key and save

    Paste the key only into the app’s field, never into a chat or to anyone

  4. Open the AI chat in Cursor in Agent mode

  5. Try it

    Use DAG Studio WebMCP and tell me what you can do for me, then show me one thing

    ✓ If Cursor says it is using DAG Studio WebMCP or shows a DAG Studio WebMCP 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 5 min

You need a DAG Studio WebMCP key (create it on the maker’s site)

  1. Sign up and create a DAG Studio WebMCP key

    Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.

    Open the DAG Studio WebMCP site ↗

  2. Click this button to open VS Code

    Open in VS Code

    VS Code asks you to confirm; click Install

  3. Fill in your key

    In the DAG Studio WebMCP settings, Authorization is empty; add your key and save

    Paste the key only into the app’s field, never into a chat or to anyone

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

  5. Try it

    Use DAG Studio WebMCP and tell me what you can do for me, then show me one thing

    ✓ If VS Code says it is using DAG Studio WebMCP or shows a DAG Studio WebMCP 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://dag-studio-webmcp-bridge.jdiazdecaro.workers.dev/mcp

JSON settings are under “For developers” below

Stuck? Ask people who use DAG Studio WebMCP💬 Discussion →
For developers: Terminal commands and JSON settings

Over the web

Claude Code

claude mcp add --transport http --scope user dag-studio-webmcp https://dag-studio-webmcp-bridge.jdiazdecaro.workers.dev/mcp --header 'Authorization: Bearer your-value'

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "dag-studio-webmcp": {
      "url": "https://dag-studio-webmcp-bridge.jdiazdecaro.workers.dev/mcp",
      "headers": {
        "Authorization": "Bearer your-value"
      }
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "dag-studio-webmcp": {
      "type": "http",
      "url": "https://dag-studio-webmcp-bridge.jdiazdecaro.workers.dev/mcp",
      "headers": {
        "Authorization": "Bearer your-value"
      }
    }
  }
}

Values you fill in

  • Authorization secret required HTTP header
    Open the studio, select Connect MCP, enable a connection, and copy its full Authorization header. Keep the page open. Expires in two hours.

Descriptions are as written by the maker.

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
Apache-2.0
Connection
Runs in the cloud
Transport
streamable-http
Latest versioni
1.0.0
Categoryi
Other
Published to registryi
Sep 7, 2026
Code last changedi
Nov 12, 2026
Last checked
Nov 14, 2026
Maker
Black-Swan-Causal-Labs
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

ClaudeGooseLM 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

The server asks you to sign in before it lists its tools.

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 19, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account Black-Swan-Causal-Labs, which owns the repo

  • ✓ Pass

    Still maintained

    Code last changed 7 days ago

  • ✓ Pass

    Has a licence

    Uses Apache-2.0

  • ✓ Pass

    Endpoint responds

    Responded in 103 ms (HTTP 401)

  • ✓ Pass

    Sign-in with OAuth

    Declares OAuth sign-in, so your AI app can take you to log in

  • … Not checked yet

    No hidden instructions in tool descriptions

    Not checked yet; we read the tool list when we check the endpoint

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/black-swan-causal-labs-dag-studio-webmcp.svg)](https://mcp.popnx.com/en/servers/black-swan-causal-labs-dag-studio-webmcp)

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 0% of the other 20693 servers in this category
  • Published to the registry more recently than 28% of the other 20693 servers in this category
  • Basic checks equal to or better than 99% of the other 20693 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 DAG Studio WebMCP 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?

You need to fill in: Authorization

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 2 months 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 3 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 30 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
DAG Studio WebMCP
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 keyYesNoNoNoNoNo
Add with + in ClaudeNoNoNoNoNoNo
Basic checks5/54/44/44/41/44/4
LicenseApache-2.0AGPL-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.

DAG Studio WebMCP

A human–AI causal DAG workspace for the OpenAI 2026 WebMCP Challenge.

The AI proposes. The researcher decides. The engine verifies.

Live HTTPS sandbox · Original DAG Studio · Apache 2.0 License

The problem

Causal directed acyclic graphs encode scientific assumptions: which variables cause which, what is measured or latent, and which paths may bias an effect estimate. Those decisions require domain expertise and scientific accountability. A general-purpose agent can help a researcher inspect and edit a graph, but visual browser automation is slow, ambiguous, and disconnected from the application's causal semantics.

DAG Studio WebMCP turns the existing DAG Studio interface into a shared workspace. A researcher can edit the canvas directly while an agent reads and updates that exact same graph through structured browser-native tools. Every agent mutation is visible and undoable. The causal engine checks the implications of the graph; neither the engine nor the agent claims to determine scientific truth.

Why WebMCP matters

Without WebMCP, an agent must infer node identities, edge directions, and analysis controls from pixels and DOM structure. With WebMCP, DAG Studio explicitly exposes safe, purpose-built operations such as add_node, add_edge, and analyze_current_dag.

This enables a two-way collaboration that was difficult before:

  1. The agent can read the live graph without scraping the interface.
  2. The agent can propose a precise, attributed change.
  3. The researcher immediately sees, moves, edits, accepts, or undoes it.
  4. Human canvas edits are immediately visible to the agent.
  5. The existing causal engine verifies backdoor paths and adjustment implications.
  6. The agent can simulate reproducible data under competing DAG hypotheses and compare their structural and statistical implications.

Live demonstration

Open the sandbox in ChatGPT's WebMCP-capable browser or Chrome with chrome://flags/#enable-webmcp-testing enabled. The header displays WebMCP connected when tools are available.

Suggested prompt:

Read the current DAG. Propose Smoking Status as a possible confounder, add it with arrows to Treatment and Outcome, then analyze the graph. Treat the additions as assumptions for my review and do not make any other changes.

The graph updates in place. Move the new node manually, then ask the agent to read the graph again to demonstrate that both participants share the same state.

WebMCP tools

ToolBehavior
get_current_dagReads live nodes, roles, positions, directed edges, exposure, and outcome.
add_nodeAdds a researcher-reviewable variable to the visible canvas.
remove_nodeRemoves a node and its incident edges.
add_edgeAdds a directed causal claim; duplicate, self, and cyclic edges are rejected.
remove_edgeRemoves a directed causal claim.
analyze_current_dagReturns open backdoor paths, minimal sufficient adjustment sets, identifiability, and diagnostics. Identifiability is exact at any graph size; a flag marks when the list of minimal sets is not exhaustive.
check_adjustment_setChecks whether a proposed set is a valid adjustment set: it must block every encoded backdoor path and contain no descendant of the exposure (such as a mediator). Reports both conditions.
generate_analysis_codeGenerates R/dagitty or Python/NetworkX code for the live graph.
simulate_current_dagRuns the existing linear Gaussian SEM for the live graph, opens the visible simulation result, and returns bounded summaries, correlations, effect estimates, and a 10-row preview.

The integration prefers the current document.modelContext API and includes a temporary navigator.modelContext fallback for hosts implementing an earlier WebMCP draft.

Architecture

Researcher edits canvas ─┐

├─ React state + synchronous refs ─ DAG Studio engine Agent calls WebMCP tools ┘ │ ├─ paths and adjustment sets ├─ diagnostics ├─ R/Python generation └─ reproducible simulation summaries

  • index.html contains the existing React DAG Studio interface.
  • webmcp-tools.js defines and registers the nine tools through dependency-injected access to the canvas's state refs, mutation wrappers, and existing simulation engine.
  • dag-engine.js and dag-engine.d.ts are the existing DAG Studio causal engine and type declarations. The Challenge work calls this engine; it does not rewrite its causal algorithms.
  • The graph, analysis, undo history, and WebMCP operations remain client-side.
  • The static build is hosted over HTTPS on Cloudflare Pages.

Human control and safety

Causal structure is an assertion, not a fact discovered by software. Tool descriptions and responses therefore frame mutations as proposals for researcher review. Agent changes:

  • appear on the same canvas used for human editing;
  • receive a visible agent-change notification;
  • enter the same undo history as human changes;
  • reject graph cycles and invalid node references; and
  • return an explicit caveat that results depend on the encoded assumptions.

Examples and the wider interface

The inherited DAG Studio interface includes canonical structures for confounding, mediation, collider bias, and M-bias, along with:

  • drag-and-drop DAG editing and typed variables;
  • exposure and outcome designation;
  • highlighted causal and backdoor paths;
  • minimal adjustment guidance and structural-role diagnostics;
  • R and Python code generation and code-to-canvas workflows;
  • client-side data simulation; and
  • image, PDF, PowerPoint, and code export.

What existed before August 25, 2026

The pre-Challenge baseline is the public Black-Swan-Causal-Labs/dag-studio application at commit 31cc431612ba18a8bce1ab0841a88a0bb8b815f3, dated July 8, 2026. It already contained the visual DAG editor, causal inference engine, educational examples, analysis panels, code console, simulation, export, and responsive UI.

The original application did not expose WebMCP tools, attribute agent graph edits, or test human/agent access to one shared graph state.

Built specifically for the WebMCP Challenge

The following work was added during the Challenge submission period after August 25, 2026:

  • nine WebMCP tools, including reproducible simulation of the live DAG;
  • direct wiring from those tools to the canvas's existing shared state;
  • WebMCP connection diagnostics and current/earlier API compatibility;
  • visible, undoable agent-change attribution;
  • automated tests for tool registration, agent mutations, human-to-agent state visibility, edge/node removal, cycle rejection, engine analysis, adjustment checks, code generation, simulation reproducibility, bounded results, and input validation;
  • an isolated HTTPS sandbox that does not alter production DAG Studio; and
  • Challenge-specific documentation and demo instructions.

Run locally

git clone https://github.com/Black-Swan-Causal-Labs/dag-studio-webmcp.git

cd dag-studio-webmcp npm install npm run dev

Open the printed Vite URL. To expose native WebMCP in Chrome, enable chrome://flags/#enable-webmcp-testing and relaunch Chrome.

Test and build

npm test

npm run build

The test command runs both the original DAG engine parity suite and the WebMCP/shared-state suite. The production build is a static dist/ directory suitable for any HTTPS static host.

Scientific basis

The causal engine implements d-separation and adjustment logic based on Pearl (2009), Greenland, Pearl & Robins (1999), and Textor et al. (2016). Effect-modification classification follows VanderWeele & Robins (2007) and Weinberg (2007). See the in-app About and Education sections for details.

Author and license

John D. Diaz-Decaro, PhD, MS · Black Swan Causal Labs

Apache License 2.0 © 2026 John D. Diaz-Decaro, Black Swan Causal Labs, LLC. See LICENSE.

The reused dag-engine.js and dag-engine.d.ts files originate in DAG Studio and are shared with dagstudio-mcp. All three projects distribute the engine under Apache License 2.0; the WebMCP Challenge work calls the engine without rewriting its causal algorithms.

Remote MCP clients

An optional remote MCP bridge connects other MCP clients to the same live browser canvas. Open the app, select Connect MCP, and enable a temporary connection. Native WebMCP continues to work without pairing. Registry metadata is in server.json.