Matlab MCP Server Python vs ScratchRun
A side-by-side look at the Matlab MCP Server Python and ScratchRun MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Matlab MCP Server Python for code execution work as a local process; choose ScratchRun for code execution as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Matlab MCP Server Python when
- You need dedicated capabilities in the Code Execution domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You have the keys it needs:
MATLAB_MCP_POOL_MATLAB_ROOT. - You want tools like
execute_code, check_code, get_workspace.
Choose ScratchRun when
- You need dedicated capabilities in the Code Execution domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
SCRATCHRUN_API_KEY.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Code Execution | Code Execution |
| Quality signal | 53/100 · Good | 40/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | Not declared |
| Pricing | Paid service | Not declared |
| Required env vars | MATLAB_MCP_POOL_MATLAB_ROOT | SCRATCHRUN_API_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 4 | 0 |
| Directory activity | 2 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 20 | Not listed |
| Full listing | View Matlab MCP Server Python | View ScratchRun |
Tools & capabilities
Matlab MCP Server Python tools 20
execute_codeRun MATLAB code. Returns inline if fast (<30s), or a job ID if promoted to asynccheck_codeRun `checkcode`/`mlint`. Returns structured warnings/errorsget_workspaceShow variables in the current MATLAB workspaceget_job_statusStatus + progress percentage for running jobsget_job_resultFull result of a completed jobcancel_jobCancel a pending or running joblist_jobsList all jobs in this sessionlist_toolboxesList installed MATLAB toolboxeslist_functionsList functions in a toolboxget_helpGet MATLAB help text for any functionupload_dataUpload data files to the sessiondelete_fileDelete a session file- +8 more on the listing page
ScratchRun tools
No tool names declared yet. Check the project README from the listing page.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Matlab MCP Server Python
{
"mcpServers": {
"hansur94-matlab-mcp-server-python": {
"command": "uvx",
"args": [
"matlab-mcp-python"
],
"env": {
"MATLAB_MCP_POOL_MATLAB_ROOT": "YOUR_MATLAB_MCP_POOL_MATLAB_ROOT_HERE"
}
}
}
}
ScratchRun
{
"mcpServers": {
"scratchrun": {
"command": "npx",
"args": [
"-y",
"@scratchrun/mcp-server"
],
"env": {
"SCRATCHRUN_API_KEY": "YOUR_SCRATCHRUN_API_KEY_HERE"
}
}
}
}
Frequently asked questions
Matlab MCP Server Python is categorized under Code Execution and uses a local stdio subprocess. ScratchRun belongs to Code Execution and uses a local stdio subprocess. Pick Matlab MCP Server Python for code execution work and ScratchRun for code execution.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Matlab MCP Server Python is listed as a paid service. Auth: no auth required. ScratchRun has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add hansur94-matlab-mcp-server-python and scratchrun as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Matlab MCP Server Python has a quality signal of 53/100 (Good) with 2 views, 0 installs and 4 GitHub stars. ScratchRun has 40/100 (Fair) with 0 views, 0 installs and 0 GitHub stars.