Buzzterms
Read-only glossary of technology and business terms, with explanations and learning paths.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"buzzterms": {
"url": "https://buzzterms.com/api/mcp"
}
}
}遠端端點
https://buzzterms.com/api/mcpstreamable-http它能做什麼
工具清單
工具（8）
🟢search_terms(query, limit)
Find glossary entries by name, alias, or explanatory keywords when you do not know the ID. Supports multiword and bounded typo matching. Returns ranked summaries with score, matchedOn, and absolute url links; use get_term for full content.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "A name, alias, or useful keywords, for example \"retrieval augmented\" or the typo \"kubernets\"."
},
"limit": {
"default": 10,
"description": "Maximum entries to return: default 10, maximum 50.",
"type": "integer",
"minimum": 1,
"maximum": 50
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_term(id)
Get one glossary entry with its full definition, plain-English explanation, example, sources, and absolute url. Use this to explain or cite a specific concept. Accepts an ID, title, or alias. Includes everydayMeaning and an optional everydayMeaningNote when available; unknown names may return suggestions, and ambiguous names need an exact ID.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"description": "Entry ID, title, or alias, for example \"rag\", \"Vector Database\", or \"retrieval augmented generation\"."
}
},
"required": [
"id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_related_terms(detail, id)
Explain a concept in context by getting it together with the glossary entries editors linked as related, in their chosen order, with absolute url links. Accepts an ID, title, or alias. Neighbors default to full; compact detail shortens neighbors while keeping the main entry full.
輸入結構描述
{
"type": "object",
"properties": {
"detail": {
"description": "\"full\" returns complete related entries (default); \"compact\" returns neighbor summaries. The main entry always stays full.",
"type": "string",
"enum": [
"compact",
"full"
]
},
"id": {
"type": "string",
"minLength": 1,
"description": "Entry ID, title, or alias, for example \"rag\", \"Vector Database\", or \"retrieval augmented generation\"."
}
},
"required": [
"id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢list_categories
Discover the glossary's broad topic areas and their IDs, absolute url links, member IDs (termIds), and counts (termCount). Use get_category to read a topic's entries.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_category(detail, limit, cursor, id)
Get a topic area, its membership and link, and its glossary entries. ID-only requests return all entries in full. Adding detail, limit, or cursor enables pages (25 default, 100 maximum); detail defaults full. total counts the full topic. Use list_categories to discover IDs and get_term for a full entry.
輸入結構描述
{
"type": "object",
"properties": {
"detail": {
"description": "\"full\" returns complete entries (default); \"compact\" returns summaries with links.",
"type": "string",
"enum": [
"compact",
"full"
]
},
"limit": {
"description": "Entries per page: default 25, maximum 100. May change between pages.",
"type": "integer",
"minimum": 1,
"maximum": 100
},
"cursor": {
"description": "Copy nextCursor from the previous page and keep the same tool, filters, and detail. Omit it on the first request; restart without it after INVALID_CURSOR. The final page has no nextCursor.",
"type": "string",
"minLength": 1,
"maxLength": 2048
},
"id": {
"type": "string",
"minLength": 1,
"description": "Topic ID from list_categories, for example \"ai-and-automation\" or \"cloud-and-systems\"."
}
},
"required": [
"id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢list_lines
Discover editor-curated learning paths. Each path lists its ID, absolute url, count (termCount), and entry IDs (termIds) in recommended order. Use get_line to read a path.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_line(detail, id)
Get a learning path, its membership and absolute url, and all its glossary entries in recommended order. Use this to learn a topic step by step. Entries default to full explanations; compact detail returns summaries. Use list_lines to discover path IDs.
輸入結構描述
{
"type": "object",
"properties": {
"detail": {
"description": "\"full\" returns complete entries (default); \"compact\" returns summaries with links.",
"type": "string",
"enum": [
"compact",
"full"
]
},
"id": {
"type": "string",
"minLength": 1,
"description": "Learning-path ID from list_lines, for example \"cloud-foundations\" or \"ai-foundations\"."
}
},
"required": [
"id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢list_terms(categoryId, lineId, limit, cursor)
Browse compact glossary summaries with absolute url links when you want an overview rather than a keyword search. Optional topic and learning-path filters intersect. Entries keep glossary order, including when filtered by path; use get_line for path order. Pages default to 25, maximum 100; total counts all filtered entries. Use get_term for full content.
輸入結構描述
{
"type": "object",
"properties": {
"categoryId": {
"description": "Topic ID from list_categories, for example \"ai-and-automation\" or \"cloud-and-systems\".",
"type": "string",
"minLength": 1
},
"lineId": {
"description": "Learning-path ID from list_lines, for example \"cloud-foundations\" or \"ai-foundations\".",
"type": "string",
"minLength": 1
},
"limit": {
"default": 25,
"description": "Entries per page: default 25, maximum 100. May change between pages.",
"type": "integer",
"minimum": 1,
"maximum": 100
},
"cursor": {
"description": "Copy nextCursor from the previous page and keep the same tool, filters, and detail. Omit it on the first request; restart without it after INVALID_CURSOR. The final page has no nextCursor.",
"type": "string",
"minLength": 1,
"maxLength": 2048
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}社群
證據