Official MathWorks MCP server that lets Claude detect MATLAB installations, inspect toolboxes, analyze MATLAB files, evaluate MATLAB code, run scripts, run tests, and expose reviewed custom MATLAB functions as MCP tools.
MATLAB MCP Core Server can start MATLAB, connect to an existing MATLAB instance, evaluate arbitrary MATLAB code, run scripts, and run MATLAB test files., The evaluate and run tools can change files, workspace state, figures, models, generated artifacts, or external systems depending on the MATLAB code being executed., Custom extension files can expose additional MATLAB functions as MCP tools, so review the JSON definition and the corresponding MATLAB functions before startup., The README advises reviewing all tool calls and keeping a human in the loop before running important actions., Shared or centralized server use is restricted by upstream licensing guidance; check MathWorks terms before team or service deployments.
Privacy notes
Tool calls can expose MATLAB code, command-window output, project folder names, installed toolbox versions, add-ons, scripts, tests, model outputs, plots, logs, and local file paths., The README states anonymized usage data collection is on by default and can be disabled with `--disable-telemetry=true`., Log folders, stderr duplication, extension-file paths, MATLAB roots, and initial working folders can reveal local machine or project context., If MATLAB code calls external services, reads private data, or writes generated outputs, those effects are part of the approved tool call and may be visible to the MCP client and model provider.
Author
MathWorks
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
5 prerequisites to line up before setup. Includes a review or approval gate.
0/5 ready
Install & runtime3Review & approval220 minutes
Safety & privacy surface
Safety & privacy surface
5 safety and 4 privacy notes across 6 risk areas. Review closely: network access, third-party handling.
6 areas
SafetyNetwork accessMATLAB MCP Core Server can start MATLAB, connect to an existing MATLAB instance, evaluate arbitrary MATLAB code, run scripts, and run MATLAB test files.
SafetyLocal filesThe evaluate and run tools can change files, workspace state, figures, models, generated artifacts, or external systems depending on the MATLAB code being executed.
SafetyLocal filesCustom extension files can expose additional MATLAB functions as MCP tools, so review the JSON definition and the corresponding MATLAB functions before startup.
SafetyExecution & processesThe README advises reviewing all tool calls and keeping a human in the loop before running important actions.
SafetyGeneralShared or centralized server use is restricted by upstream licensing guidance; check MathWorks terms before team or service deployments.
PrivacyLocal filesTool calls can expose MATLAB code, command-window output, project folder names, installed toolbox versions, add-ons, scripts, tests, model outputs, plots, logs, and local file paths.
PrivacyTelemetryThe README states anonymized usage data collection is on by default and can be disabled with `--disable-telemetry=true`.
PrivacyLocal filesLog folders, stderr duplication, extension-file paths, MATLAB roots, and initial working folders can reveal local machine or project context.
PrivacyThird-party handlingIf MATLAB code calls external services, reads private data, or writes generated outputs, those effects are part of the approved tool call and may be visible to the MCP client and model provider.
Disclosure: Official MathWorks source-available MCP server. The repository license permits redistribution with conditions and restricts use to MathWorks products and service offerings; MATLAB itself requires an appropriate MathWorks license.
Safety notes
MATLAB MCP Core Server can start MATLAB, connect to an existing MATLAB instance, evaluate arbitrary MATLAB code, run scripts, and run MATLAB test files.
The evaluate and run tools can change files, workspace state, figures, models, generated artifacts, or external systems depending on the MATLAB code being executed.
Custom extension files can expose additional MATLAB functions as MCP tools, so review the JSON definition and the corresponding MATLAB functions before startup.
The README advises reviewing all tool calls and keeping a human in the loop before running important actions.
Shared or centralized server use is restricted by upstream licensing guidance; check MathWorks terms before team or service deployments.
Privacy notes
Tool calls can expose MATLAB code, command-window output, project folder names, installed toolbox versions, add-ons, scripts, tests, model outputs, plots, logs, and local file paths.
The README states anonymized usage data collection is on by default and can be disabled with `--disable-telemetry=true`.
Log folders, stderr duplication, extension-file paths, MATLAB roots, and initial working folders can reveal local machine or project context.
If MATLAB code calls external services, reads private data, or writes generated outputs, those effects are part of the approved tool call and may be visible to the MCP client and model provider.
Prerequisites
MATLAB R2021a or later installed under a valid MathWorks license.
Claude Code, Claude Desktop, VS Code, or another MCP client that can run a local stdio server.
Release binary, source build, or Claude Desktop MCPB bundle downloaded from the upstream repository.
Project folders and MATLAB files reviewed before allowing Claude to run code against them.
Optional MATLAB extension-file JSON reviewed before enabling custom tools.
Schema details
Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
20 minutes
Difficulty
advanced
Tool listing metadata
Disclosure
Official MathWorks source-available MCP server. The repository license permits redistribution with conditions and restricts use to MathWorks products and service offerings; MATLAB itself requires an appropriate MathWorks license.
MATLAB MCP Core Server is the official MathWorks MCP server for connecting AI
applications to MATLAB. It runs as a local stdio server and can connect Claude
Code, Claude Desktop, VS Code, or another MCP client to a licensed MATLAB
installation.
Use it when Claude needs MATLAB-specific context instead of generic file access:
installed toolbox discovery, MATLAB Code Analyzer findings, reviewed code
evaluation, script execution, MATLAB test execution, or custom tools backed by
MATLAB functions already on the MATLAB path.
These sources were reviewed on 2026-06-06. Prefer the live repository,
README, license, server entry point, CLI parameter definitions, tool definition
source, custom tool guide, and telemetry factory for current behavior.
Features
Run as a local stdio MCP server named matlab-mcp-core-server.
Detect installed MATLAB versions and toolboxes.
Start MATLAB on demand or initialize MATLAB when the server starts.
Connect to a new MATLAB process, an existing MATLAB instance, or automatic
session selection.
Analyze .m files with MATLAB Code Analyzer without modifying the file.
Evaluate reviewed MATLAB code in an existing MATLAB context.
Run selected MATLAB scripts and return command-window output.
Run MATLAB test files through MATLAB's test framework.
Expose custom MATLAB functions as MCP tools through reviewed extension-file
JSON definitions.
Provide MATLAB coding guideline and plain-text live-code resources.
Disable upstream usage telemetry with --disable-telemetry=true.
Installation
Download the upstream release binary, build from source, or install the Claude
Desktop MCPB bundle from the repository release page. Then add the stdio server
to your MCP client.
When using Claude Desktop, review the upstream MCPB and any filesystem access
you grant through other extensions. When using custom MATLAB tools, inspect the
extension JSON and the MATLAB functions it exposes before starting the server.
Use Cases
Ask Claude to identify installed MATLAB toolboxes before choosing an analysis
approach.
Run MATLAB Code Analyzer on a reviewed .m file and discuss warnings.
Execute a small MATLAB snippet after checking the exact code Claude plans to
run.
Run a project script in a known working folder and inspect command-window
output.
Run MATLAB unit tests after a code change.
Expose a narrow, reviewed MATLAB function as a custom MCP tool for repeatable
calculations.
Pair Claude with MATLAB for scientific computing, simulation, signal
processing, control systems, image processing, or engineering workflows where
MATLAB is already the approved environment.
Safety and Privacy
Treat this server as a code-execution bridge into MATLAB, not as a passive
documentation helper. MATLAB code can read and write files, start computations,
open graphical tools, create models and figures, call external services, and
change project state. Review the exact tool arguments before approving
evaluation, script execution, test execution, or custom tool calls.
The server can reveal sensitive context through command-window output, installed
toolbox lists, add-ons, project folders, code paths, logs, generated results,
and test output. Upstream documentation says anonymized usage telemetry is on by
default; add --disable-telemetry=true when you do not want that collection.
Check MathWorks licensing guidance before shared, centralized, classroom,
enterprise, or service-style deployments.
Duplicate Check
No matlab/matlab-mcp-core-server, MATLAB MCP Core Server, MathWorks MCP
server, or matching MATLAB MCP source URL entry was found in content/mcp or
README.md.
Show that MATLAB MCP Core Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/matlab-mcp-core-server)
How it compares
MATLAB MCP Core Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
1 trust signal differ across this comparison (Submitter).
Official MathWorks MCP server that lets Claude detect MATLAB installations, inspect toolboxes, analyze MATLAB files, evaluate MATLAB code, run scripts, run tests, and expose reviewed custom MATLAB functions as MCP tools.
Local-first codebase intelligence MCP server that indexes repositories with tree-sitter, stores searchable chunks in DuckDB, and gives Claude semantic search, regex search, daemon status, and deep code research tools.
Code intelligence MCP server with a Zig core for local project indexing, structural outlines, symbol lookup, search, dependency graphs, snapshots, remote public-repo queries, and fallback edits.
Manage A/B tests and feature flags in GrowthBook from Claude — list and create experiments, toggle rollouts, review test results, and interact with your GrowthBook workspace — with the official GrowthBook MCP server.
✓MATLAB MCP Core Server can start MATLAB, connect to an existing MATLAB instance, evaluate arbitrary MATLAB code, run scripts, and run MATLAB test files.
The evaluate and run tools can change files, workspace state, figures, models, generated artifacts, or external systems depending on the MATLAB code being executed.
Custom extension files can expose additional MATLAB functions as MCP tools, so review the JSON definition and the corresponding MATLAB functions before startup.
The README advises reviewing all tool calls and keeping a human in the loop before running important actions.
Shared or centralized server use is restricted by upstream licensing guidance; check MathWorks terms before team or service deployments.
✓ChunkHound reads source files, Markdown, text, PDFs, and supported config files under the target directory and stores indexed chunks in a local database.
Realtime indexing and daemon mode can continue watching project files after the initial MCP connection.
Code research and web search tools require embedding, reranking, and LLM configuration and may invoke local CLIs or external model APIs depending on settings.
Exclude generated files, vendored dependencies, secrets, large artifacts, and unrelated repositories before indexing broad workspace roots.
Review MCP client configuration carefully when using an absolute project path in a global Claude Desktop config.
✓CodeDB indexes local projects and exposes file tree, outline, search, symbol, caller, dependency, read, snapshot, project, and context tools to the MCP client.
CodeDB's `codedb_edit` tool exists as a fallback editing tool and can create, replace, insert, delete, or modify files when used by a client without native edit tooling.
The npm package runs a postinstall step that downloads a native binary from GitHub Releases; review package and release provenance in environments that restrict native binaries.
Remote repo queries use the public `api.wiki.codes` service and should be treated as network access outside the local repository.
The upstream README marks the project as alpha software, with parser coverage and snapshot formats still stabilizing.
✓`create_experiment` and `create_feature` write to your GrowthBook workspace — capabilities are scoped by your API key/PAT permissions.
Creating experiments or feature flags may immediately affect production if they are in a live environment — review before confirming.
Privacy notes
✓Tool calls can expose MATLAB code, command-window output, project folder names, installed toolbox versions, add-ons, scripts, tests, model outputs, plots, logs, and local file paths.
The README states anonymized usage data collection is on by default and can be disabled with `--disable-telemetry=true`.
Log folders, stderr duplication, extension-file paths, MATLAB roots, and initial working folders can reveal local machine or project context.
If MATLAB code calls external services, reads private data, or writes generated outputs, those effects are part of the approved tool call and may be visible to the MCP client and model provider.
✓Indexed chunks, file paths, symbols, comments, Markdown, PDFs, configuration values, database files, daemon state, and search results can reveal proprietary source code and internal architecture.
Embedding, reranking, LLM, and web search providers may receive code-derived queries or snippets if configured.
Local ChunkHound database files, logs, daemon state, and MCP transcripts may retain code-derived context after the session ends.
Avoid sharing ChunkHound databases, config files with API keys, verbose logs, research outputs, and screenshots from private repositories.
✓Local indexes, snapshots, file trees, symbol names, dependency graphs, snippets, read results, and search results can reveal proprietary code structure and implementation details.
Upstream documents sensitive-file blocking for patterns such as environment files, credentials, and keys, but users should still review ignore rules and avoid indexing secret-heavy directories.
CodeDB writes telemetry to `~/.codedb/telemetry.ndjson` unless `CODEDB_NO_TELEMETRY=1` is set, then syncs aggregate tool counts, latency, startup, file count, line count, language, version, and platform data on MCP session close.
Upstream telemetry docs state that source code, file contents, file paths, and search queries are not collected.
Remote public-repo queries and local MCP responses may still be logged by MCP clients, model providers, and terminal history.
✓Experiment configurations, feature flag definitions, targeting rules, and experiment results from your GrowthBook workspace are surfaced in Claude's context.
Your `GB_API_KEY` is a secret — store it as an environment variable, not in version-controlled config files.
Prerequisites
MATLAB R2021a or later installed under a valid MathWorks license.
Claude Code, Claude Desktop, VS Code, or another MCP client that can run a local stdio server.
Release binary, source build, or Claude Desktop MCPB bundle downloaded from the upstream repository.
Project folders and MATLAB files reviewed before allowing Claude to run code against them.
Python 3.10 or newer and the `uv` package manager.
A local repository or workspace you are authorized to index.
ChunkHound JSON config reviewed for database path, excludes, embeddings, and LLM provider settings.
Optional embedding provider credentials for semantic search, or regex-only usage when no embedding key is configured.
macOS or Linux on x64 or arm64 for the published native binary launcher.
Node.js 18 or newer when using the `codedeebee` npm launcher.
A local project directory that the MCP client exposes through roots or launches from.
Review of which local repositories, file types, generated artifacts, and secrets patterns may be indexed.
A GrowthBook account (cloud at growthbook.io or self-hosted).
A GrowthBook API key (from API Keys settings or a Personal Access Token with appropriate permissions).
Your GrowthBook account email (used when creating experiments and feature flags).
Node.js with `npx` available.
Install
Download the release binary or Claude Desktop MCPB bundle, review the MathWorks license terms, then add the stdio server command to your MCP client.