mplus-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mplus_statusA | Report which Mplus executable will be used, its version, and any demo-version limits. Call this first when a run fails for reasons that look like the installation rather than the model. |
| syntax_helpA | Mplus syntax reference by topic: overview, data, variable, analysis, model, mediation, cfa, invariance, growth, mixture, multilevel, output, fit, montecarlo, errors, demo. Call with no topic to list them. Use it before writing syntax for a model family you have not written recently. |
| data_prepareA | Convert a CSV, Excel, SPSS (.sav), Stata (.dta) or parquet file into an Mplus .dat file: numeric only, no header, missing values flagged, names cut to 8 characters. Returns the DATA and VARIABLE block to paste into an input file, plus a per-variable summary and a note of anything that was renamed or recoded. |
| build_syntaxA | Write Mplus input syntax for a standard model family (cfa, efa, path, sem, mediation, growth, lpa, lca, invariance, twolevel, custom). Returns the syntax as text - it does not run it. Read it, adjust it, then pass it to |
| run_syntaxA | Write Mplus input syntax to a file, run it, and summarise the output. Long lines are folded to the 90-character limit first. The .inp and .out stay on disk. Use |
| run_fileA | Run an Mplus input file that already exists on disk and summarise the output. Use this for .inp files written by hand or by the Mplus editor. |
| output_summaryA | Summarise an Mplus .out file that already exists: status, warnings, fit, parameter estimates, and whatever else |
| output_sectionA | Return one section of an .out file verbatim, for anything the summary does not parse - TECH1, TECH4, residuals, sample statistics, random-start loglikelihoods. Call without |
| compare_fitA | Put the fit statistics of several .out files side by side - class enumeration, measurement invariance, nested model comparisons. With |
| savedata_readA | Read the file a SAVEDATA command wrote - factor scores, class probabilities, most likely class membership - using the column layout Mplus recorded at the end of the .out file. Optionally write it out as a CSV for use in R or Excel. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Each tool has a clearly distinct role in the Mplus workflow: installation status, syntax reference, data conversion, syntax generation, execution from text versus file, parsed output summarization versus raw sections, cross-file comparison, and savedata ingestion. No two tools overlap enough to cause selection ambiguity.
All names are lowercase snake_case and readable, but they mix verb-first forms (build_syntax, run_syntax, run_file, compare_fit), output_* prefixed forms, and noun-verb forms (data_prepare, savedata_read). The functional prefixes help, but the ordering is not consistent enough for a higher score.
Ten tools is well within the ideal range and each one maps to a distinct stage of the Mplus analysis lifecycle. None of the tools feel redundant or unnecessary for the server's stated purpose.
The set covers the full workflow: checking installation, syntax help, data preparation, syntax generation, running new or existing input files, summarizing output, retrieving raw output sections, comparing model fits, and reading SAVEDATA files. There are no obvious dead ends or significant missing operations.