list-topics
Returns a list of topics for which resources (web pages, etc ...) have been crawled and content is available. This allows AI assistants to discover the most relevant and up-to-date subject areas currently indexed by the crawler.
無需輸入參數。

io.github.CloudCorpRecords由 GitHub 帳號 CloudCorpRecords 發布v0.1.0更新於 Nov 7, 2026
Search Driflyte's topic-indexed crawled web knowledge: list topics and retrieve documents.
Knowdrift 讓助理列出依主題索引的網頁爬取所涵蓋的主題,並從該索引中擷取與問題最相關的文件。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
參照 儲存庫 中的啟動說明。
knowdrift connects an MCP client to a web crawl that is organised by topic. Instead of searching the open web blindly, you first ask which topics the crawler has already covered, then pull the documents it filed under the topics that match your question. Answers come back as ranked documents drawn from pages that were actually crawled and indexed.
This package is a thin forwarding client. It speaks MCP over stdio on one side and relays each tool call to the public remote service over streamable HTTP on the other, returning whatever the remote sends back.
list-topicsTakes no arguments. Returns the names of the topics for which crawled content is currently available, so you can discover the subject areas the index covers before searching it.
searchRetrieves the documents that best match a question inside chosen topics.
The tool subcommands accept the tool's arguments as a single JSON object string and print the first text block of the result. Exit codes are 0 on success, 1 when the call returns an error result, and 2 for usage errors.
Start the stdio server with the mcp subcommand:
MCP client configuration:
With no arguments the container runs the stdio MCP server; any other arguments are passed to the CLI.
No account or API key is needed: the upstream service is public. When the upstream cannot be reached or answers with an error, the tool returns an error result whose text begins with knowdrift error: rather than fabricating documents.
The test suite runs fully offline. It drives the forwarding logic against a stubbed JSON-RPC upstream and checks the served tool list against the documented tool surface.
MIT — see LICENSE.
來源:README.md,提交 72b8bb8
Returns a list of topics for which resources (web pages, etc ...) have been crawled and content is available. This allows AI assistants to discover the most relevant and up-to-date subject areas currently indexed by the crawler.
無需輸入參數。
Given a list of topics and a user question, this tool retrieves the top-K most relevant documents from the crawled content. It is designed to help AI assistants surface the most contextually appropriate and up-to-date information for a specific topic and query.
topKquery必填topics必填已滿足適用檢查項的 90%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
npx @reneturcios/knowdrift list-topicsnpx @reneturcios/knowdrift search '{"topics":["technology"],"query":"How do vector databases work?","topK":5}'npx @reneturcios/knowdrift --versionnpx -y @reneturcios/knowdrift mcp{ "mcpServers": { "knowdrift": { "command": "npx", "args": ["-y", "@reneturcios/knowdrift", "mcp"] } }}docker run -i ghcr.io/cloudcorprecords/knowdriftdocker run --rm ghcr.io/cloudcorprecords/knowdrift search '{"topics":["technology"],"query":"What is new in quantum computing?"}'npm installnpm run buildnpm testnpm run dev