# Dictionary of Applied Machine Learning (remote · dictionaryofml.org)

Look up, search and cross-reference machine-learning terms from dictionaryofml.org.

- Trust score: 69/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- remote · `dictionaryofml.org`: 69/100 (this document), [markdown](https://verifymcp.io/servers/org-dictionaryofml-dictionary/dictionaryofml.md), [page](https://verifymcp.io/servers/org-dictionaryofml-dictionary/dictionaryofml)

## Channel facts

- Endpoint: `https://dictionaryofml.org/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 80/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 4253 tokens (~33/item across 126 items; 6 tools + 120 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Dictionary of Applied Machine Learning MCP server?

Dictionary of Applied Machine Learning is a hosted endpoint at https://dictionaryofml.org/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http org-dictionaryofml-dictionary 'https://dictionaryofml.org/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "org-dictionaryofml-dictionary": {
      "url": "https://dictionaryofml.org/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "org-dictionaryofml-dictionary": {
      "type": "http",
      "url": "https://dictionaryofml.org/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.org-dictionaryofml-dictionary]
url = "https://dictionaryofml.org/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "org-dictionaryofml-dictionary": {
      "type": "remote",
      "url": "https://dictionaryofml.org/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add org-dictionaryofml-dictionary --url 'https://dictionaryofml.org/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  org-dictionaryofml-dictionary:
    url: "https://dictionaryofml.org/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "org-dictionaryofml-dictionary": {
      "Transport": "http",
      "Url": "https://dictionaryofml.org/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add org-dictionaryofml-dictionary -t streamable-http -u 'https://dictionaryofml.org/mcp'
```

### Other

```json
{
  "mcpServers": {
    "org-dictionaryofml-dictionary": {
      "type": "http",
      "url": "https://dictionaryofml.org/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-03 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 68, 0)

- [functional] New resource “base learner”
- [functional] New resource “correlation”
- [functional] New resource “decision boundary”

### 2026-11-01 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 67, 0)

- [functional] New resource “inverse”

### 2026-10-30 (score 67, +1)

- [functional] New resource “effective dimension”

### 2026-10-29 (score 66, +3)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 133 → 4097
- [functional] The server now declares the “resources” capability
- [functional] First check of Schema quality: 100
- [functional] Schema quality: fair → good
- [functional] New resource “Gaussian mixture model (GMM)”
- [functional] New resource “Gaussian random variable (Gaussian RV)”
- [functional] New resource “Hilbert space”
- [functional] New resource “Reading order: Erklärbare & vertrauenswürdige KI”
- [functional] New resource “Reading order: KI in der Praxis (ML-Systeme)”
- [functional] New resource “Reading order: KI, Recht & AI Act”
- [functional] New resource “Reading order: KI-Grundlagen”
- [functional] New resource “Reading order: Mathematik der KI”
- [functional] New resource “Reading order: Wie funktioniert ChatGPT? (LLMs)”
- [functional] New resource “Sobolev space”
- [functional] New resource “accuracy”
- [functional] New resource “artificial neural network (ANN)”
- [functional] New resource “attention”
- [functional] New resource “autoencoder”
- [functional] New resource “backpropagation”
- [functional] New resource “bagging”
- [functional] New resource “baseline”
- [functional] New resource “binary classification”
- [functional] New resource “boosting”
- [functional] New resource “bootstrap”
- [functional] New resource “classification”
- [functional] New resource “clustering”
- [functional] New resource “concept activation vector (CAV)”
- [functional] New resource “confusion matrix”
- [functional] New resource “convex”
- [functional] New resource “covariance matrix”
- [functional] New resource “data”
- [functional] New resource “data augmentation”
- [functional] New resource “data imputation”
- [functional] New resource “data leakage”
- [functional] New resource “data point”
- [functional] New resource “dataset”
- [functional] New resource “decision tree”
- [functional] New resource “dimensionality reduction”
- [functional] New resource “distribution shift”
- [functional] New resource “eigenvalue”
- [functional] New resource “eigenvalue decomposition (EVD)”
- [functional] New resource “empirical risk minimization (ERM)”
- [functional] New resource “ensemble”
- [functional] New resource “expectation–maximization (EM)”
- [functional] New resource “explainability”
- [functional] New resource “explainable artificial intelligence (XAI)”
- [functional] New resource “explanation”
- [functional] New resource “fairness (machine learning)”
- [functional] New resource “feature”
- [functional] New resource “feature importance”
- [functional] New resource “feature learning”
- [functional] New resource “feature matrix”
- [functional] New resource “feature vector”
- [functional] New resource “fine-tuning”
- [functional] New resource “generalization”
- [functional] New resource “gradient”
- [functional] New resource “gradient descent (GD)”
- [functional] New resource “hyperparameter”
- [functional] New resource “hypothesis”
- [functional] New resource “hypothesis space”
- [functional] New resource “independent and identically distributed (i.i.d.)”
- [functional] New resource “independent and identically distributed assumption (i.i.d. assumption)”
- [functional] New resource “inner product”
- [functional] New resource “interpretability”
- [functional] New resource “interpretable machine learning (interpretable ML)”
- [functional] New resource “k-fold cross-validation (k-fold CV)”
- [functional] New resource “k-means”
- [functional] New resource “kernel method”
- [functional] New resource “kernel ridge regression”
- [functional] New resource “label”
- [functional] New resource “large language model (LLM)”
- [functional] New resource “learning rate”
- [functional] New resource “linear classifier”
- [functional] New resource “linear regression”
- [functional] New resource “logistic loss”
- [functional] New resource “logistic regression”
- [functional] New resource “loss”
- [functional] New resource “machine learning pipeline (ML pipeline)”
- [functional] New resource “matrix”
- [functional] New resource “mean”
- [functional] New resource “membership inference attack”
- [functional] New resource “model”
- [functional] New resource “model selection”
- [functional] New resource “norm”
- [functional] New resource “online learning”
- [functional] New resource “overfitting”
- [functional] New resource “policy (reinforcement learning)”
- [functional] New resource “pretraining”
- [functional] New resource “principal component analysis (PCA)”
- [functional] New resource “probability distribution”
- [functional] New resource “projection”
- [functional] New resource “random experiment”
- [functional] New resource “random forest”
- [functional] New resource “random variable (RV)”
- [functional] New resource “regularization”
- [functional] New resource “reinforcement learning (RL)”
- [functional] New resource “reward”
- [functional] New resource “robust principal component analysis (robust PCA)”
- [functional] New resource “sample size”
- [functional] New resource “self-supervised learning”
- [functional] New resource “sigmoid function”
- [functional] New resource “singular value decomposition (SVD)”
- [functional] New resource “stochastic gradient descent (SGD)”
- [functional] New resource “supervised learning”
- [functional] New resource “support vector machine (SVM)”
- [functional] New resource “tabular data”
- [functional] New resource “test set”
- [functional] New resource “training”
- [functional] New resource “training error”
- [functional] New resource “training set”
- [functional] New resource “transfer learning”
- [functional] New resource “transformer”
- [functional] New resource “transparency”
- [functional] New resource “trusted execution environment (TEE)”
- [functional] New resource “trustworthy artificial intelligence (trustworthy AI)”
- [functional] New resource “unsupervised learning”
- [functional] New resource “validation error”
- [functional] New resource “validation set”
- [functional] New resource “variance”
- [functional] New tool “get_learning_path”
- [functional] New tool “list_learning_paths”

### 2026-10-28 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 62, 0)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (6)

### `list_all_terms` (~24 tokens)

List every term of the Dictionary of Applied Machine Learning (name and key).

### `lookup_term` (~36 tokens)

Full dictionary entry (abstract, definition, cross-references) for a term, by key or name.

Input parameters:

- `term` (string, required)

### `search_terms` (~38 tokens)

Search term names and definitions for a keyword or phrase; returns the best matches.

Input parameters:

- `limit` (integer)
- `query` (string, required)

### `get_related_terms` (~35 tokens)

The terms a given entry cross-references (its See-also list), with their abstracts.

Input parameters:

- `term` (string, required)

### `list_learning_paths` (~81 tokens)

The author's curated reading orders through the dictionary: one per topic (how ChatGPT works, AI foundations, explainable and trustworthy AI, mathematics of AI, ...), each with its audience and its terms in the order to read them. Use when someone asks what to learn, read, or teach about a topic, or how to structure a course or seminar.

### `get_learning_path` (~86 tokens)

One reading order with the abstract of every term in it. Give `topic` (a path id or words from its title or audience), or `terms` (an explicit list of term keys or names, kept in the given order) — the form a selection on alexjung.at/baukasten/ takes.

Input parameters:

- `terms` (array)
- `topic` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/org-dictionaryofml-dictionary/dictionaryofml#diagnostics

## Score history

- 2026-11-04: 69
- 2026-11-03: 69
- 2026-11-02: 68
- 2026-11-01: 68
- 2026-10-31: 67
- 2026-10-30: 67
- 2026-10-29: 66
- 2026-10-28: 63
- 2026-10-27: 62
- 2026-10-26: 62

## Common questions

### What is the Dictionary of Applied Machine Learning MCP server?

Dictionary of Applied Machine Learning is an MCP server listed in the public MCP registry as org.dictionaryofml/dictionary. Look up, search and cross-reference machine-learning terms from dictionaryofml.org. This page covers its hosted endpoint (https://dictionaryofml.org/mcp).

### Is the Dictionary of Applied Machine Learning MCP server safe to use?

Dictionary of Applied Machine Learning scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Dictionary of Applied Machine Learning MCP server expose?

Dictionary of Applied Machine Learning exposes 6 tools: list_all_terms, lookup_term, search_terms, get_related_terms, list_learning_paths, get_learning_path. Their descriptions and schemas cost roughly 300 tokens of context every time the server is loaded.

### Does the Dictionary of Applied Machine Learning MCP server require authentication?

No. We connected to Dictionary of Applied Machine Learning without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Dictionary of Applied Machine Learning MCP server still maintained?

Dictionary of Applied Machine Learning is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://dictionaryofml.org/mcp
- Repository: https://github.com/alexjungaalto/dictionaryofml
- Website: https://dictionaryofml.org/
- Changelog RSS feed: https://verifymcp.io/servers/org-dictionaryofml-dictionary/dictionaryofml.xml
- Changelog JSON feed: https://verifymcp.io/servers/org-dictionaryofml-dictionary/dictionaryofml.json
- HTML version of this page: https://verifymcp.io/servers/org-dictionaryofml-dictionary/dictionaryofml