catalog
Search Avva for an expert, then connect their model - judgment from real past decisions.
我該用這個嗎
品質與安全性
A
發現項目(1)
- LOW在 fetch 中
根據工具定義與協定合規性的自動化分析。
上下文成本
~449Token(工具定義)
~2.0 KB典型回應大小
極小的注意力影響(128k 上下文的 0.35%)
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": {
"catalog": {
"url": "https://avva.chat/mcp-catalog"
}
}
}遠端端點
https://avva.chat/mcp-catalogstreamable-http它能做什麼
工具清單
工具(2)
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢search(query)
Find published experts by domain, decision types, or wording. Returns result ids for fetch. Read-only.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 500,
"description": "What kind of judgment you are looking for."
}
},
"required": [
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
}
},
"required": [
"id",
"title",
"url"
],
"additionalProperties": false
}
}
},
"required": [
"results"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢fetch(id)
Full catalog card for one expert by id (their slug), including the MCP connector URL your agent connects to consult them. Read-only.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1,
"maxLength": 120,
"description": "An id returned by search."
}
},
"required": [
"id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}輸出結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"text": {
"type": "string"
},
"url": {
"type": "string"
},
"metadata": {
"type": "object",
"properties": {
"connector_url": {
"type": "string"
},
"profile_url": {
"type": "string"
},
"kind": {
"type": "string",
"enum": [
"expert",
"house"
]
},
"coverage": {
"type": "string"
}
},
"required": [
"connector_url",
"profile_url",
"kind",
"coverage"
],
"additionalProperties": false
}
},
"required": [
"id",
"title",
"text",
"url"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}建議的提示詞
find_specific
Find [specific item] using catalog
預期的工具:
searchfetch_info
Fetch [information type] using catalog
預期的工具:
fetchsearch_research
Search for information about [topic] using catalog
預期的工具:
searchretrieve_data
Get details about [item] from catalog
預期的工具:
fetchresearch_workflow
Search for [topic], then get detailed information about the top results using catalog
預期的工具:
searchfetch社群
證據
近期觀測
已驗證未記錄版本2 個工具
已驗證未記錄版本2 個工具