MCP.Market

dashAI (unofficial) MCP server

by Maarmapa·io.github.Maarmapa/dashai-mcp·v0.3.1
No reviews yet

Train, track and query models on a running dashAI instance. Read-oriented, no delete tools.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars25 downloads/wk

Reviews

Write one

Nobody has reviewed dashAI (unofficial) yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

dashAI (unofficial) tools (10, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • dashai_describe_dataset

    Returns everything needed to configure a training run over a dataset.

  • dashai_get_prediction

    Returns class counts for a finished prediction — never the rows.

  • dashai_get_runwrite action

    Returns the configuration and metrics of a training run.

  • dashai_job_status

    Polls the status of an enqueued job (training, prediction, explanation).

  • dashai_list_components

    Lists the registered components: models, metrics, tasks and optimizers.

  • dashai_list_datasets

    Lists the datasets loaded in dashAI.

  • dashai_list_runs

    Lists the recorded training runs, with their status.

  • dashai_predict

    Enqueues a prediction using the model of an already finished run.

  • dashai_server_info

    Checks that dashAI is running and summarizes what is loaded.

  • dashai_train_model

    Trains a model on a dataset and returns the id of the enqueued job.

Public scan report

scanner v0.1.10 · 2026-10-03 · same rubric, same numbers if you re-run it

no findings
  • Code scan6 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 18 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How dashAI (unofficial) compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 95% of 48,255 servers
Tools
10
the typical server has 7
Tools that change things
10%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
25
more than 11% of 12,191 servers with a package

What its tools let an agent do: 9 read · 1 change

Install dashAI (unofficial) in Claude Code, Cursor or VS Code

claude mcp add dashai-mcp -- uvx dashai-mcp
Add to Cursor

What the publisher says

From the dashAI (unofficial) repository's README, as published. We do not edit it. Read it on GitHub

dashai-mcp

<!-- mcp-name: io.github.Maarmapa/dashai-mcp -->

An MCP server for dashAI, the open source Machine Learning workbench led by the University of Chile (FCFM), built by students of DCC UChile and UTFSM, with CENIA and IMFD.

Unofficial and independent. This is a third-party project. It is not

affiliated with, endorsed by, or maintained by the dashAI project or the

institutions that develop it.

It gives an agent the same surface dashAI gives a person through its GUI: look at datasets, see which models are available, train, follow queued work, and read the metrics.

"Train a random forest on dataset 3 predicting 'species' and tell me the F1"

Status

v0.2.2 — verified against a running dashAI 0.9.7.post1. Deterministic tests (including the predict two-step path) plus live runs: dashaitrainmodel → dashaijobstatus → dashaigetrun with metrics, and dashaipredict → dashaijob_status finished.

Live tabular run (seed students)

Public dashAI seed only. Target placementstatus (~83% majority). examscore was left out of the inputs (it leaks the label). Split 70/15/15. Goal metric: BalancedAccuracy — Accuracy and F1 on the majority class are traps.

The dummy wins F1 by always answering the majority class. The linear model beats the forest on the metrics that actually measure separation. Each row is its own 70/15/15 draw (not the same test rows) — still enough to stop treating the forest as the default. If a client reports only F1 here, it is lying.

dashaipredict on the finished forest run returned predictionid and the job finished. That scores the same seed dataset the model was trained on, not a held-out file — do not read it as a generalization check. dashaigetprediction returns {n, nclasses, classcounts} only.

Live image run (seed cifar10-subset)

Public seed: 200 images, frog vs truck (100/100). LeNet5ImageClassifier, CPU, 32×32. Split 70/15/15 → test n=30. Chance is 0.5.

\Accuracy, not BalancedAccuracy — on the one-class val/test they collapse. Chance on this seed is 0.5**. Dummy tabular does not apply (image task).

The image path works. The 0.867 is not a result: dashAI defaulted shuffle=False, so val/test were 30 trucks and zero frogs. MCC 0 is sklearn on a one-class split. After this server sent shuffle=true + stratify=true, both classes are in val/test and MCC is no longer 0. Train hits 1.0 (140 images memorized). Val 0.767 is the honest-ish number; test 0.900 is a 30-row lottery. Do not publish a leaderboard line.

Verifying against a live instance surfaced gaps between dashAI's documentation and its actual behaviour. Each one has its own regression test. A sixth — sequential splits with shuffle=False — only showed up live because MCC came back 0 next to a moving Accuracy. dashaipredict sending runid to PredictJob — only showed up live (KeyError: 'prediction_id') because there was no predict test.

Install

pip install dashai-mcp
# or: uv pip install dashai-mcp

In your MCP client configuration:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

dashAI (unofficial): common questions

Is dashAI (unofficial) MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the dashAI (unofficial) safety report
How do I install dashAI (unofficial)?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does dashAI (unofficial) need an API key?
No secret keys are declared. It reads 3 settings from the environment.
Is dashAI (unofficial) maintained?
The last commit was 50 days ago (2026-09-15). The latest release is v0.3.1.
How does dashAI (unofficial) compare with other MCP servers?
safety score 92/100 (higher than 95% of 48,255 servers); tools 10 (the typical server has 7); tools that change things 10% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.