Context Link
One semantic search across your sites, Drive, Notion, email, files and Basecamp.
我該用這個嗎
品質與安全性
A
根據工具定義與協定合規性的自動化分析。
上下文成本
~1,196Token（工具定義）
~2.8 KB典型回應大小
中等的注意力影響（128k 上下文的 0.93%）
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": {
"context-link": {
"url": "https://www.context-link.ai/mcp"
}
}
}遠端端點
https://www.context-link.ai/mcpstreamable-http它能做什麼
工具清單
工具（4）
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢get_context(query, mode, connection_type)
Get context from the user's connected workspaces and websites. The attached widget displays only the list of sources consulted — it does not show the retrieved content, so use the returned context to answer the user directly.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"mode": {
"type": "string",
"description": "Optional mode to weight results (e.g. 'customer-support')"
},
"connection_type": {
"type": "string",
"description": "Optional comma-separated list of connection types to restrict retrieval to (e.g. \"site,email\"). Only content from those sources is considered. Valid types: basecamp, custom, email, files, google_doc, memory, monday, notion, one_drive, site, webmention, youtube."
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"sources": {
"type": "array",
"items": {
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"success",
"no_content",
"signup_required"
]
},
"id": {
"type": "integer"
},
"title": {
"type": "string"
},
"post_titles": {
"type": "array",
"items": {
"type": "string"
}
},
"connection_type": {
"type": "string"
},
"chunks_count": {
"type": "integer"
},
"logo": {
"type": "string"
}
},
"required": [
"kind"
]
}
},
"context": {
"type": [
"string",
"null"
]
}
},
"required": [
"sources",
"context"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢ask_question(query, mode, connection_type)
Ask a question about the user's connected workspaces and websites and receive a concise answer with citations. The attached widget displays only the list of sources consulted — it does not show the answer, so always relay the answer text in your reply.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"mode": {
"type": "string",
"description": "Optional mode to weight results (e.g. 'customer-support')"
},
"connection_type": {
"type": "string",
"description": "Optional comma-separated list of connection types to restrict retrieval to (e.g. \"site,email\"). Only content from those sources is considered. Valid types: basecamp, custom, email, files, google_doc, memory, monday, notion, one_drive, site, webmention, youtube."
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"answer": {
"type": "string",
"description": "Concise paragraph answer; empty string when success is false"
},
"citations": {
"type": "array",
"items": {
"type": "object",
"properties": {
"n": {
"type": "integer"
},
"title": {
"type": "string"
},
"url": {
"type": [
"string",
"null"
]
}
},
"required": [
"n",
"title"
],
"additionalProperties": false
}
},
"success": {
"type": "boolean"
},
"reason": {
"type": "string",
"enum": [
"ok",
"no_context",
"llm_error",
"empty_input",
"auth_required",
"signup_required",
"pro_required",
"allowance_exceeded",
"invalid_connection_type"
]
},
"sources": {
"type": "array",
"items": {
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"success",
"no_content",
"signup_required"
]
},
"id": {
"type": "integer"
},
"title": {
"type": "string"
},
"post_titles": {
"type": "array",
"items": {
"type": "string"
}
},
"connection_type": {
"type": "string"
},
"chunks_count": {
"type": "integer"
},
"logo": {
"type": "string"
}
},
"required": [
"kind"
],
"additionalProperties": false
}
}
},
"required": [
"answer",
"citations",
"success",
"reason",
"sources"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🔴save_memory(content, namespace)
Save content to the user's memory for later retrieval. Use this when the user wants to save information, notes, or conversation content.
輸入結構描述
{
"type": "object",
"properties": {
"content": {
"type": "string",
"description": "The content to save. Can be plain text, markdown, or structured content."
},
"namespace": {
"type": "string",
"description": "A name/label for this memory (use-dashes-for-spaces). If omitted, a timestamped name is generated."
}
},
"required": [
"content"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"message": {
"type": "string"
},
"namespace": {
"type": "string"
}
},
"required": [
"message",
"namespace"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_memory(namespace)
Retrieve previously saved memory content by its namespace. Use this when the user wants to recall saved content.
輸入結構描述
{
"type": "object",
"properties": {
"namespace": {
"type": "string",
"description": "The namespace/name of the saved memory to retrieve"
}
},
"required": [
"namespace"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}輸出結構描述
{
"type": "object",
"properties": {
"content": {
"type": "string"
},
"namespace": {
"type": "string"
},
"found": {
"type": "boolean"
}
},
"required": [
"content",
"namespace",
"found"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}建議的提示詞
retrieve_data
Get details about [item] from Context Link
預期的工具：
get_contextfetch_info
Fetch [information type] using Context Link
預期的工具：
get_context社群
證據
近期觀測
已驗證未記錄版本4 個工具
已驗證未記錄版本4 個工具