Dictionary of Applied Machine Learning is an MCP server published by org.dictionaryofml, hosted at dictionaryofml.org. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 6 tools, including list_all_terms, lookup_term, search_terms, get_related_terms, list_learning_paths.
Look up, search and cross-reference machine-learning terms from dictionaryofml.org.
Nothing else in the archive shares these values.
Inferred from the host name and headers: what a server runs on, not who runs it.
List every term of the Dictionary of Applied Machine Learning, one per line, as its display name followed by its key. Takes no arguments. Use it to find the key for a term before calling one of the tools that takes one.
No parameters.
{
"name": "list_all_terms",
"title": "List every term",
"description": "List every term of the Dictionary of Applied Machine Learning, one per line, as its display name followed by its key. Takes no arguments. Use it to find the key for a term before calling one of the tools that takes one.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
The full dictionary entry for one term: its abstract, its definition, the works it cites and its cross-references. Use it when a specific term is already known; use search_terms when it is not.
| Parameter | Type | Description |
|---|---|---|
| term * | string | A term, given either as its key (the lowercase one-word identifier, e.g. 'erm', 'gradientdescent') or as its display name (e.g. 'empirical risk minimization'). Matching is case-insensitive and tolerates small differences in spelling; an input that resembles no published term returns a message saying… |
{
"name": "lookup_term",
"title": "Read one entry",
"description": "The full dictionary entry for one term: its abstract, its definition, the works it cites and its cross-references. Use it when a specific term is already known; use search_terms when it is not.",
"inputSchema": {
"type": "object",
"required": [
"term"
],
"properties": {
"term": {
"type": "string",
"description": "A term, given either as its key (the lowercase one-word identifier, e.g. 'erm', 'gradientdescent') or as its display name (e.g. 'empirical risk minimization'). Matching is case-insensitive and tolerates small differences in spelling; an input that resembles no published term returns a message saying so rather than a wrong entry."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Search the term names, abstracts and definitions for a keyword or phrase and return the best matches, each with its abstract. Use it when the right term is not known in advance.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | How many matches to return, best first. Defaults to 8. |
| query * | string | The words to search for, e.g. 'overfitting' or 'gradient step size'. Matching is case-insensitive; a term whose name contains the query ranks above one where only the definition does. |
{
"name": "search_terms",
"title": "Search the dictionary",
"description": "Search the term names, abstracts and definitions for a keyword or phrase and return the best matches, each with its abstract. Use it when the right term is not known in advance.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 8,
"maximum": 50,
"minimum": 1,
"description": "How many matches to return, best first. Defaults to 8."
},
"query": {
"type": "string",
"minLength": 1,
"description": "The words to search for, e.g. 'overfitting' or 'gradient step size'. Matching is case-insensitive; a term whose name contains the query ranks above one where only the definition does."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}The terms one entry cross-references, its See-also list, each with its abstract. Use it to widen a topic by one step from a term already in hand.
| Parameter | Type | Description |
|---|---|---|
| term * | string | A term, given either as its key (the lowercase one-word identifier, e.g. 'erm', 'gradientdescent') or as its display name (e.g. 'empirical risk minimization'). Matching is case-insensitive and tolerates small differences in spelling; an input that resembles no published term returns a message saying… |
{
"name": "get_related_terms",
"title": "Follow the cross-references",
"description": "The terms one entry cross-references, its See-also list, each with its abstract. Use it to widen a topic by one step from a term already in hand.",
"inputSchema": {
"type": "object",
"required": [
"term"
],
"properties": {
"term": {
"type": "string",
"description": "A term, given either as its key (the lowercase one-word identifier, e.g. 'erm', 'gradientdescent') or as its display name (e.g. 'empirical risk minimization'). Matching is case-insensitive and tolerates small differences in spelling; an input that resembles no published term returns a message saying so rather than a wrong entry."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}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. Takes no arguments. Use when someone asks what to learn, read, or teach about a topic, or how to structure a course or seminar, so the answer follows the author's order instead of an improvised one.
No parameters.
{
"name": "list_learning_paths",
"title": "List the reading orders",
"description": "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. Takes no arguments. Use when someone asks what to learn, read, or teach about a topic, or how to structure a course or seminar, so the answer follows the author's order instead of an improvised one.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}One reading order with the abstract of every term in it, in the order to read them. Give either `topic` or `terms`; giving neither returns the list of available reading orders.
| Parameter | Type | Description |
|---|---|---|
| terms | array | An explicit reading order instead of a curated one: term keys or display names, kept in the given order. This is the form a selection on alexjung.at/baukasten/ takes, whose URL fragment reads '#terms=llm,transformer'. |
| topic | string | Which reading order to return: a path id (e.g. 'llm', 'grundlagen', 'mathematik') or words from its title or its audience note. Matching is case-insensitive. |
{
"name": "get_learning_path",
"title": "Read one reading order",
"description": "One reading order with the abstract of every term in it, in the order to read them. Give either `topic` or `terms`; giving neither returns the list of available reading orders.",
"inputSchema": {
"type": "object",
"properties": {
"terms": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 1,
"description": "An explicit reading order instead of a curated one: term keys or display names, kept in the given order. This is the form a selection on alexjung.at/baukasten/ takes, whose URL fragment reads '#terms=llm,transformer'."
},
"topic": {
"type": "string",
"minLength": 1,
"description": "Which reading order to return: a path id (e.g. 'llm', 'grundlagen', 'mathematik') or words from its title or its audience note. Matching is case-insensitive."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}The Dictionary of Applied Machine Learning (dictionaryofml.org), an open course edition maintained by Alexander Jung at Aalto University. Each entry defines one machine-learning term precisely, with cross-references, citations and, for most terms, a Python demo that recomputes what the entry states. Consult it when a question turns on what a machine-learning term means, how two terms differ, or which notation a definition uses: the entries are written to be quoted, and lookup_term returns one in full. search_terms finds entries by keyword when the exact term is unknown, and get_related_terms walks the cross-reference graph. When someone asks what to read, learn, or teach about a topic, list_learning_paths gives the author's curated reading orders (topic, audience, terms in order) and get_learning_path returns one of them, or the entries for an explicit list of terms in that order. Entries are citable; each term page carries a BibTeX block.
Names, descriptions and schemas were written by the server and are shown as data.