Results for
MATLAB MCP Core Server v0.6.0 has been released onGitHub: https://github.com/matlab/matlab-mcp-core-server/releases/tag/v0.6.0
Release highlights:
- New cross-platform MCP Bundle; one-click installation in Claude Desktop
Enhancements:
- Provide structured output from check_matlab_code and additional information for MATLAB R2022b onwards
- Made project_path optional in evaluate_matlab_code tool for simpler tool calls
- Enhanced detect_matlab_toolboxes output to include product version
Bug fixes:
- Updated MCP Go SDK dependency to address CVE.
We encourage you to try this repository and provide feedback. If you encounter a technical issue or have an enhancement request, create an issue https://github.com/matlab/matlab-mcp-core-server/issues
Web Automation with Claude, MATLAB, Chromium, and Playwright
Duncan Carlsmith, University of Wisconsin-Madison
Introduction
Recent agentic browsers (Chrome with Claude Chrome extension and Comet by Perplexity) are marvelous but limited. This post describes two things: first, a personal agentic browser system that outperforms commercial AI browsers for complex tasks; and second, how to turn AI-discovered web workflows into free, deterministic MATLAB scripts that run without AI.
My setup is a MacBook Pro with the Claude Desktop app, MATLAB 2025b, and Chromium open-source browser. Relevant MCP servers include fetch, filesystem, MATLAB, and Playwright, with shell access via MATLAB or shell MCP. Rather than use my Desktop Chrome application, which might expose personal information, I use an independent, dedicated Chromium with a persistent login and preauthentication for protected websites. Rather than screenshots, which quickly saturate a chat context and are expensive, I use the Playwright MCP server, which accesses the browser DOM and accessibility tree directly. DOM manipulation permits error-free operation of complex web page UIs.
The toolchain required is straightforward. You need Node.js , which is the JavaScript runtime that executes Playwright scripts outside a browser. Install it, then set up a working directory and install Playwright with its bundled Chromium:
# Install Node.js via Homebrew (macOS) or download from nodejs.org
brew install node
# Create a working directory and install Playwright
mkdir MATLABWithPlaywright && cd MATLABWithPlaywright
npm init -y
npm install playwright
# Download Playwright's bundled Chromium (required for Tier 1)
npx playwright install chromium
That is sufficient for the Tier 1 examples. For Tier 2 (authenticated automation), you also need Google Chrome or the open-source Chromium browser, launched with remote debugging enabled as described below. Playwright itself is an open-source browser automation library from Microsoft that can either launch its own bundled browser or connect to an existing one -- this dual capability is the foundation of the two-tier architecture. For the AI-agentic work described in the Canvas section, you need Claude Desktop with MCP servers configured for filesystem access, MATLAB, and Playwright. The INSTALL.md in the accompanying FEX submission covers all of this in detail.
AI Browser on Steroids: Building Canvas Quizzes
An agentic browser example just completed illustrates the power of this approach. I am adding a computational thread to a Canvas LMS course in modern physics based on relevant interactive Live Scripts I have posted to the MATLAB File Exchange. For each of about 40 such Live Scripts, I wanted to build a Canvas quiz containing an introduction followed by a few multiple-choice questions and a few file-upload questions based on the "Try this" interactive suggestions (typically slider parameter adjustments) and "Challenges" (typically to extend the code to achieve some goal). The Canvas interface for quiz building is quite complex, especially since I use a lot of LaTeX, which in the LMS is rendered using MathJax with accessibility features and only a certain flavor of encoding works such that the math is rendered both in the quiz editor and when the quiz is displayed to a student.
My first prompt was essentially "Find all of my FEX submissions and categorize those relevant to modern physics.” The categories emerged as Relativity, Quantum Mechanics, Atomic Physics, and Astronomy and Astrophysics. Having preauthenticated at MathWorks with a Shibboleth university license authentication system, the next prompt was "Download and unzip the first submission in the relativity category, read the PDF of the executed script or view it under examples at FEX, then create quiz questions and answers as described above." The final prompt was essentially "Create a new quiz in my Canvas course in the Computation category with a due date at the end of the semester. Include the image and introduction from the FEX splash page and a link to FEX in the quiz instructions. Add the MC quiz questions with 4 answers each to select from, and the file upload questions. Record what you learned in a SKILL file in my MATLAB/claude/SKILLS folder on my filesystem." Claude offered a few options, and we chose to write and upload the quiz HTML from scratch via the Canvas REST API. Done. Finally, "Repeat for the other FEX File submissions." Each took a couple of minutes. The hard part was figuring out what I wanted to do exactly.
Mind you, I had tried to build a Canvas quiz including LaTeX and failed miserably with both Chrome Extension and Comet. The UI manipulations, especially to handle the LaTeX, were too complex, and often these agentic browsers would click in the wrong place, wind up on a different page, even in another tab, and potentially become destructive.
A key gotcha with LaTeX in Canvas: the equation rendering system uses double URL encoding for LaTeX expressions embedded as image tags pointing to the Canvas equation server. The LaTeX strings must use single backslashes -- double backslashes produce broken output. And Canvas Classic Quizzes and New Quizzes handle MathJax differently, so you need to know which flavor your institution uses.
From AI-Assisted to Programmatic: The Two-Tier Architecture
An agentic-AI process, like the quiz creation, can become expensive. There is a lot of context, both physics content-related and process-related, and the token load mounts up in a chat. Wouldn't it be great if, after having used the AI for what it is best at -- summarizing material, designing student exercises, and discovering a web-automation process -- one could repeat the web-related steps programmatically for free with MATLAB? Indeed, it would, and is.
In my setup, usually an AI uses MATLAB MCP to operate MATLAB as a tool to assist with, say, launching an application like Chromium or to preprocess an image. But MATLAB can also launch any browser and operate it via Playwright. (To my knowledge, MATLAB can use its own browser to view a URL but not to manipulate it.) So the following workflow emerges:
1) Use an AI, perhaps by recording the DOM steps in a manual (human) manipulation, to discover a web-automation process.
2) Use the AI to write and debug MATLAB code to perform the process repeatedly, automatically, for free.
I call this "temperature zero" automation -- the AI contributes entropy during workflow discovery, then the deterministic script is the ground state.
The architecture has three layers:
MATLAB function (.m)
|
v
Generate JavaScript/Playwright code
|
v
Write to temporary .js file
|
v
Execute: system('node script.js')
|
v
Parse output (JSON file or console)
|
v
Return structured result to MATLAB
The .js files serve double duty: they are both the runtime artifacts that MATLAB generates and executes, AND readable documentation of the exact DOM interactions Playwright performs. Someone who wants to adapt this for their own workflow can read the .js file and see every getByRole, fill, press, and click in sequence.
Tier 1: Basic Web Automation Examples
I have demonstrated this concept with three basic examples, each consisting of a MATLAB function (.m) that dynamically generates and executes a Playwright script (.js). These use Playwright's bundled Chromium in headless mode -- no authentication required, no persistent sessions.
01_ExtractTableData
extractTableData.m takes a URL and scrapes a complex Wikipedia table (List of Nearest Stars) that MATLAB's built-in webread cannot handle because the table is rendered by JavaScript. The function generates extract_table.js, which launches Playwright's bundled Chromium headlessly, waits for the full DOM to render, walks through the table rows extracting cell text, and writes the result as JSON. Back in MATLAB, the JSON is parsed and cleaned (stripping HTML tags, citation brackets, and Unicode symbols) into a standard MATLAB table.
T = extractTableData(...
'https://en.wikipedia.org/wiki/List_of_nearest_stars_and_brown_dwarfs');
disp(T(1:5, {'Star_name', 'Distance_ly_', 'Stellar_class'}))
histogram(str2double(T.Distance_ly_), 20)
xlabel('Distance (ly)'); ylabel('Count'); title('Nearest Stars')
02_ScreenshotWebpage
screenshotWebpage.m captures screenshots at configurable viewport dimensions (desktop, tablet, mobile) with full-page or viewport-only options. The physics-relevant example captures the NASA Webb Telescope page at multiple viewport sizes. This is genuinely useful for checking how your own FEX submission pages or course sites look on different devices.
03_DownloadFile
downloadFile.m is the most complex Tier 1 function because it handles two fundamentally different download mechanisms. Direct-link downloads (where navigating to the URL triggers the download immediately) throw a "Download is starting" error that is actually success:
try {
await page.goto(url, { waitUntil: 'commit' });
} catch (e) {
// Ignore "Download is starting" -- that means it WORKED!
if (!e.message.includes('Download is starting')) throw e;
}
Button-click downloads (like File Exchange) require finding and clicking a download button after page load. The critical gotcha: the download event listener must be set up BEFORE navigation, not after. Getting this ordering wrong was one of those roadblocks that cost real debugging time.
The function also supports a WaitForLogin option that pauses automation for 45 seconds to allow manual authentication -- a bridge to Tier 2's persistent-session approach.
Another lesson learned: don't use Playwright for direct CSV or JSON URLs. MATLAB's built-in websave is simpler and faster for those. Reserve Playwright for files that require JavaScript rendering, button clicks, or authentication.
Tier 2: Production Automation with Persistent Sessions
Tier 2 represents the key innovation -- the transition from "AI does the work" to "AI writes the code, MATLAB does the work." The critical architectural difference from Tier 1 is a single line of JavaScript:
// Tier 1: Fresh anonymous browser
const browser = await chromium.launch();
// Tier 2: Connect to YOUR running, authenticated Chrome
const browser = await chromium.connectOverCDP('http://localhost:9222');
CDP is the Chrome DevTools Protocol -- the same WebSocket-based interface that Chrome's built-in developer tools use internally. When you launch Chrome with a debugging port open, any external program can connect over CDP to navigate pages, inspect and manipulate the DOM, execute JavaScript, and intercept network traffic. The reason this matters is that Playwright connects to your already-running, already-authenticated Chrome session rather than launching a fresh anonymous browser. Your cookies, login sessions, and saved credentials are all available. You launch Chrome once with remote debugging enabled:
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome \
--remote-debugging-port=9222 \
--user-data-dir="$HOME/chrome-automation-profile"
Log into whatever sites you need. Those sessions persist across automation runs.
addFEXTagLive.m
This is the workhorse function. It uses MATLAB's modern arguments block for input validation and does the following: (1) verifies the CDP connection to Chrome is alive with a curl check, (2) dynamically generates a complete Playwright script with embedded conditional logic -- check if tag already exists (skip if so), otherwise click "New Version", add the tag, increment the version number, add update notes, click Publish, confirm the license dialog, and verify the success message, (3) executes the script asynchronously and polls for a result JSON file, and (4) returns a structured result with action taken, version changes, and optional before/after screenshots.
result = addFEXTagLive( ...
'https://www.mathworks.com/matlabcentral/fileexchange/183228-...', ...
'interactive_examples', Screenshots=true);
% result.action is either 'skipped' or 'added_tag'
% result.oldVersion / result.newVersion show version bump
% result.screenshots.beforeImage / afterImage for display
The corresponding add_fex_tag_production.js is a standalone Node.js version that accepts command-line arguments:
node add_fex_tag_production.js 182704 interactive-script 0.01 "Added tag"
This is useful for readers who want to see the pure JavaScript logic without the MATLAB generation layer.
batch_tag_FEX_files.m
The batch controller reads a text file of URLs, loops through them calling addFEXTagLive with rate limiting (10 seconds between submissions), tracks success/skip/fail counts, and writes three output files: successful_submissions.txt, skipped_submissions.txt, and failed_submissions_to_retry.txt.
This script processed all 178 of my FEX submissions:
Total: 178 submissions processed in 2h 11m (~44 sec/submission)
Tags added: 146 (82%) | Already tagged: 32 (18%) | True failures: 0
Manual equivalent: ~7.5 hours | Token cost after initial engineering: $0
The Timeout Gotcha
An interesting gotcha emerged during the batch run. Nine submissions were reported as failures with timeout errors. The error message read:
page.textContent: Timeout 30000ms exceeded.
Call log: - waiting for locator('body')
Investigation revealed these were false negatives. The timeout occurred in the verification phase -- Playwright had successfully added the tag and clicked Publish, but the MathWorks server was slow to reload the confirmation page (>30 seconds). The tag was already saved. When a retry script ran, all nine immediately reported "Tag already exists -- SKIPPING." True success rate: 100%.
Could this have been fixed with a longer timeout or a different verification strategy? Sure. But I mention it because in a long batch process (2+ hours, 178 submissions), gotchas emerge intermittently that you never see in testing on five items. The verification-timeout pattern is a good one to watch for: your automation succeeded, but your success check failed.
Key Gotchas and Lessons Learned
A few more roadblocks worth flagging for anyone attempting this:
waitUntil options matter. Playwright's networkidle wait strategy almost never works on modern sites because analytics scripts keep firing. Use load or domcontentloaded instead. For direct downloads, use commit.
Quote escaping in MATLAB-generated JavaScript. When MATLAB's sprintf generates JavaScript containing CSS selectors with double quotes, things break. Using backticks as JavaScript template literal delimiters avoids the conflict.
The FEX license confirmation popup is accessible to Playwright as a standard DOM dialog, not a browser popup. No special handling needed, but the Publish button appears twice -- once to initiate and once to confirm -- requiring exact: true in the role selector to distinguish them:
// First Publish (has a space/icon prefix)
await page.getByRole('button', { name: ' Publish' }).click();
// Confirm Publish (exact match)
await page.getByRole('button', { name: 'Publish', exact: true }).click();
File creation from Claude's container vs. your filesystem. This caused real confusion early on. Claude's default file creation tools write to a container that MATLAB cannot see. Files must be created using MATLAB's own file operations (fopen/fprintf/fclose) or the filesystem MCP's write_file tool to land on your actual disk.
Selector strategy. Prefer getByRole (accessibility-based, most stable) over CSS selectors or XPath. The accessibility tree is what Playwright MCP uses natively, and role-based selectors survive minor UI changes that would break CSS paths.
Two Modes of Working
Looking back, the Canvas quiz creation and the FEX batch tagging represent two complementary modes of working with this architecture:
The Canvas work keeps AI in the loop because each quiz requires different physics content -- the AI reads the Live Script, understands the physics, designs questions, and crafts LaTeX. The web automation (posting to Canvas via its REST API) is incidental. This is AI-in-the-loop for content-dependent work.
The FEX tagging removes AI from the loop because the task is structurally identical across 178 submissions -- navigate, check, conditionally update, publish. The AI contributed once to discover and encode the workflow. This is AI-out-of-the-loop for repetitive structural work.
Both use the same underlying architecture: MATLAB + Playwright + Chromium + CDP. The difference is whether the AI is generating fresh content or executing a frozen script.
Reference Files and FEX Submission
All of the Tier 1 and Tier 2 MATLAB functions, JavaScript templates, example scripts, installation guide, and skill documentation described in this post are available as a File Exchange submission: Web Automation with Claude, MATLAB, Chromium, and Playwright .The package includes:
Tier 1 -- Basic Examples:
- extractTableData.m + extract_table.js -- Web table scraping
- screenshotWebpage.m + screenshot_script.js -- Webpage screenshots
- downloadFile.m -- File downloads (direct and button-click)
- Example usage scripts for each
Tier 2 -- Production Automation:
- addFEXTagLive.m -- Conditional FEX tag management
- batch_tag_FEX_files.m -- Batch processing controller
- add_fex_tag_production.js -- Standalone Node.js automation script
- test_cdp_connection.js -- CDP connection verification
Documentation and Skills:
- INSTALL.md -- Complete installation guide (Node.js, Playwright, Chromium, CDP)
- README.md -- Package overview and quick start
- SKILL.md -- Best practices, decision trees, and troubleshooting (developed iteratively through the work described here)
The SKILL.md file deserves particular mention. It captures the accumulated knowledge from building and debugging this system -- selector strategies, download handling patterns, wait strategies, error handling templates, and the critical distinction between when to use Playwright versus MATLAB's native websave. It was developed as a "memory" for the AI assistant across chat sessions, but it serves equally well as a human-readable reference.
Credits and conclusion
This synthesis of existing tools was conceived by the author, but architected (if I may borrow this jargon) by Claud.ai. This article was conceived and architected by the author, but Claude filled in the details, most of which, as a carbon-based life form, I could never remember. The author has no financial interest in MathWorks or Anthropic.
I see many people are using our new MCP Core Sever to do amazing things with MATLAB and AI. Some people are describing their experiements here (e.g. @Duncan Carlsmith) and on LinkedIn (E.g. Sergiu-Dan Stan and Toshi Takeuchi) and we are getting lots of great feedback.Some of that feedback has been addressed in the latest release so please update your install now.
MATLAB MCP Core Server v0.4.0 has been released on public GitHub:
Release highlights:
- Added Plain Text Live Code Guidelines MCP resource
- Added MCP Annotations to all tools
We encourage you to try this repository and provide feedback. If you encounter a technical issue or have an enhancement request, create an issue https://github.com/matlab/matlab-mcp-core-server/issues
At the present time, the following problems are known in MATLAB Answers itself:
- Symbolic output is not displaying. The work-around is to disp(char(EXPRESSION)) or pretty(EXPRESSION)
- Symbolic preferences are sometimes set to non-defaults
Can anyone provide insight into the intended difference between Discussions and Answers and what should be posted where?
Just scrolling through Discussions, I saw postst that seem more suitable Answers?
What exactly does Discussions bring to the table that wasn't already brought by Answers?
Maybe this question is more suitable for a Discussion ....
Similar to what has happened with the wishlist threads (#1 #2 #3 #4 #5), the "what frustrates you about MATLAB" thread has become very large. This makes navigation difficult and increases page load times.
So here is the follow-up page.
What should you post where?
Next Gen threads (#1): features that would break compatibility with previous versions, but would be nice to have
@anyone posting a new thread when the last one gets too large (about 50 answers seems a reasonable limit per thread), please update this list in all last threads. (if you don't have editing privileges, just post a comment asking someone to do the edit)
Hello everyone,
I’m Jiro, and I’m part of the Education Customer Success group at MathWorks. We help academics, students, and institutions achieve success through the use of our tools. I will be the moderator for this new community of distance learning.
As many academic institutions are moving their classes online, we hope that this community will help instructors connect with others who are in the same situation. This community site gathers various resources and information that will be useful for teaching with MATLAB and Simulink in a distance learning setting. We have a number of MathWorks employees monitoring this community, but we want this to be a place for the community to come together. The hope is that the community will grow and the resources gathered here will grow with it.
I encourage you to share best practices ( Discussions ), ask questions ( MATLAB Answers ), and share examples ( File Exchange ).
As a first question, what course are you teaching (or planning to teach) online?
After reading Rik's comment I looked for a list of Matlab releases and their corresponding features. Wiki: Matlab contains an exhaustive list, but what about having a lean version directly in the forum?
If this is useful, feel free to expand the list and to insert additions. Thank you.
Some of Matlab's toolbox functions are affected by magic strings or magic numbers, which are strings or numbers with a deeper meaning besides the normal value. Both are considered as bad programming patters, because they provoke confusions, when the magic keys appear with the normal meaning by accident. See http://en.wikipedia.org/wiki/Anti-pattern
Example 1:
clear('myVariable')
clear('variables')
While the 1st clears the variable myVariable, the later clears all variables. Here 'variables' has a meta-meaning. The problem appears, when 'variables' is an existing variable:
a = 1;
variables = 2;
clear('variables')
disp(a) % >> 1
Only variables is cleared, which cannot be understood directly when its definition is 1000 lines before.
Example 2:
uicontrol('String', 'default')
This creates a button with the empty string '' instead of the expected 'default', because this is the magic string to invoke the default value get(0, 'DefaultUIControlString'). The same concerns properties of other graphic objects also, e.g. the 'name' property of figure or the string of uimenu. There is a workaround which allows the user to display 'default': Simply use '\default'. Unfortunately this is doubled magic, because in consequence it is impossible to display the string '\default'. Obviously a bad idea.
Example 3:
Graphic handles are doubles (although gobject of the new R2013a seems, like this is subject to changes? [EDITED: Yes, it changed with HG2 in R2014a]). But then a handle can be confused with data:
a = axes; % e.g. 0.0048828125
plot(a, 2, '+')
But you cannot draw the point [0.0048828125, 2] by this way, because the 1st input is considered as handle of the parent. Here all possible values of handles are magic. Collisions are very unlikely, but there is no way to avoid them reliably - as long as handles have the type double.
Question:
Which functions are concerned by magic values? What are the pitfalls and workarounds?
Don't be shy, what was your matlab learning curve, how many years or months, what were the difficulties to begin with.
I think that the answers would be most valuable for new users, maybe you can also tell us the tricks that allowed you to master some parts or all matlab.
Now it's your turn...
I love MATLAB. It is so quick and easy to write software to do what you want. It has excellent debugging and profiling tools. It is cross platform, making code easy to share (assuming the other people have forked out for the not-so-cheap license). It has interfaces to other software.
However, there are some things about it that irk me. I'd like to hear from other people what things annoy them about MATLAB.
---------------------------------
Because this thread has become so large it is slow to load and navigate. Please post new answers in the second thread.
---------------------------------
As asked by Vieniava in "How to make a list of user's reputation?", some of us came up with interesting ideas on how to fill an updated list with the reputation scores of the contributors to Answers.
I took the initiative to compile a public list of users with meta info:
- position (desc ordering by reputation)
- id
- nickname (truncated to fit the page)
- reputation
- # of comments
- # of questions asked
- % accept rate
- # of posts answered
- # of accepted answers
The code used to compile the list is available at the bottom.
EDIT
TMW team implemented a page with the metascores: http://www.mathworks.com/matlabcentral/answers/contributors
Please refer to it and congrats to the team!
Use this function to retrieve info from the link above:
function [metainfo, elapsedTime] = metainfo(type,order)
% METAINFO - Retrieve metainfo on contributors to www.matworks.com/.../answers
%
% METAINFO Retrieve data sorted by reputation in descending order
%
% METAINFO(TYPE,ORDER) Specify TYPE and sorting ORDER as
% type : 'reputation'
% 'questions'
% 'answered'
% 'accepted'
%
% order: 'asc'
% 'desc'
%
% Examples:
%
% % Standard call (rep, disc)
% info = metainfo;
%
% % Sort by question answered in descending order
% info = metainfo('an','d');
%
% See also: URLREAD, REGEXP
% Author: Oleg Komarov (oleg.komarov@hotmail.it)
% Tested on R14SP3 (7.1) and on R2009b. In-between compatibility is assumed.
% 28 feb 2011 - Created
tic
% Check # inputs
error(nargchk(0,2,nargin))
% Retrieve inputs
if nargin == 0
type = 'reputation';
order = 'desc';
end
if ~exist(type,'var')
sortTypes = {'reputation','questions','answered','accepted'};
type = sortTypes{strncmp(type,sortTypes,numel(type))};
order = 'desc';
end
if ~exist(order,'var')
orderTypes = {'asc','desc'};
type = orderTypes{strncmp(order,orderTypes,numel(order))};
end
% Build url string
url = ['http://www.mathworks.com/matlabcentral/answers/contributors?'...
'dir=' order '&sort=' type '&page='];
% First read
[page, ok] = urlread([url '1']);
% Catch number of pages to read
if ok
totcon = regexp(page,'>1 - 50 of (\d+)','tokens');
totcon = dataread('string',totcon{1}{1},'%d');
nPages = ceil(totcon/50);
else
error('Cannot read ".../contributors?page=1"')
end
% Loop over contributors pages
metainfo = cell(totcon,7);
metainfo(1:end,1) = num2cell(1:size(metainfo,1));
for p = 1:nPages
if ok
endpos = 50*p;
% Id, Rep
expr = '><a href="\/matlabcentral\/answers\/contributors\/(\d+)';
data = regexp(page, expr,'tokens');
if 50*p > totcon; endpos = 50*(p-1)+numel(data); end
metainfo(1+(p-1)*50:endpos,2) = [data{:}];
% Nickname
expr = ['"Reputation: (\d+)">([\w\ ' reshape([repmat(92,1,137);33:59,61:64,91:97,123:126,161:255],1,[]) ']+)</a></h2>'];
data = regexp(page, expr,'tokens');
metainfo(1+(p-1)*50:endpos,[4,3]) = cat(1,data{:});
% Qcount, Ans, Acc
data = regexp(page, '<span >(\d+)</span>[A-z<>"-\s\/]+','tokens');
metainfo(1+(p-1)*50:endpos,5:7) = reshape(cat(1,data{:}),3,[]).';
else
error('Metainfo import stopped. \nCannot read ".../contributors?page=%d"',p)
end
[page, ok] = urlread([url sprintf('%d',p+1)]);
end
% Convert to doubles
metainfo(:,[2,4:7]) = cellfun(@str2double,metainfo(:,[2,4:7]),'un',false);
elapsedTime = toc;
