econ-r-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ECON_R_MCP_CONFIG | No | Path to configuration TOML file. | |
| ECON_R_MCP_ALLOWED_ROOTS | No | Absolute path(s) to allowed workspace roots, comma-separated if multiple. |
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 |
|---|---|
| health_checkA | Check local R, Rscript, Quarto, and R package availability. |
| init_projectB | Create a reproducible project folder layout inside an allowed workspace root. |
| install_r_packagesA | Install only allowlisted R packages and return structured install results. |
| run_r_scriptB | Run a project R script headlessly, saving logs, session info, and result JSON. |
| render_quartoB | Render a project Quarto report to HTML, PDF, or DOCX using the quarto executable. |
| inspect_datasetB | Inspect CSV, TSV, RDS, Parquet, or Stata data and return machine-readable summaries. |
| run_regression_fixestC | Run a fixest regression and save coefficient tables, logs, model object, and metadata. |
| run_ivC | Run an IV regression with first-stage output and weak-instrument diagnostics where available. |
| run_didC | Run DiD workflows including TWFE event studies or Callaway-Sant'Anna estimates. |
| run_rdrobustB | Run rdrobust, saving bandwidths, robust estimates, RD plot, and density check if available. |
| run_panel_diagnosticsB | Check panel balance, duplicate unit-time keys, missing periods, and treatment timing. |
| run_time_series_diagnosticsB | Run plots, ACF/PACF, unit-root checks, and structural-break diagnostics where available. |
| create_modelsummaryC | Create publication-style model tables from saved model objects or result JSON files. |
| read_artifactB | Read a saved table, log, result JSON, Markdown, HTML, or TeX artifact without executing code. |
| list_artifactsC | List run artifacts under a project with pagination. |
| reproduce_runC | Rerun a previous saved input script and compare result JSON hashes. |
| lookup_econometrics_guidanceB | Return curated econometric guidance by method tag or local corpus search. |
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 17 tools
Each tool targets a specific econometric method or workflow step, with no overlapping purposes. The run_* tools are clearly differentiated by method (DiD, IV, panel diagnostics, RD, fixest regression, time series diagnostics, generic R script), and all other tools serve distinct roles like project setup, data inspection, artifact management, and reporting.
All tool names follow a consistent verb_noun pattern using snake_case. Verbs like create, init, inspect, install, list, lookup, read, render, reproduce, and run are appropriately paired with nouns. Even 'health_check' can be seen as a noun phrase but functions as a verb, and the pattern is uniform across the set.
Seventeen tools is well-suited for an econometrics-focused MCP server. The count covers essential workflow stages—project setup, data inspection, package management, multiple econometric methods, diagnostics, model summary, artifact handling, reproducibility, and reporting—without being excessive or sparse.
The tool surface covers a broad range of econometric methods (DiD, IV, RD, panel diagnostics, time series diagnostics, fixest regression) and supporting tasks. Minor gaps exist, such as no dedicated tool for basic OLS regression (though fixest can handle it) or data transformation, but overall the set is comprehensive for its stated domain.