Knowdrift

io.github.CloudCorpRecordsPublished by GitHub account CloudCorpRecordsv0.1.0Updated Nov 7, 2026

Search Driflyte's topic-indexed crawled web knowledge: list topics and retrieve documents.

VerifiedSTDIODesktop onlyWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Knowdrift lets an assistant list the topics covered by a topic-indexed web crawl and retrieve ranked documents from that index for a question.

What you can do
  • List the topics for which crawled web content is currently available
  • Search within one or more chosen topics and get the top-K most relevant documents, ranked by semantic relevance (up to 30, default 10)
  • Forward each call to a public remote service and return its results, or an error result if the upstream fails
When to use it
Useful when you want answers grounded in a curated, topic-organised crawl rather than a blind open-web search, and you are fine with the topics and documents the index already covers.
Requirements
Runs locally as a stdio process via npx (Node.js) or the Docker image; it relays calls over streamable HTTP to a public remote endpoint. No account or API key is needed. Optional environment variables DRIFLYTE_MCP_URL (upstream endpoint override) and REQUEST_TIMEOUT_MS (default 30000) can be set.
Before you install
Queries and chosen topics are sent to the third-party remote service at the configured endpoint, so avoid confidential questions. Setting DRIFLYTE_MCP_URL redirects all traffic to another host. The server is read-only and returns an error result rather than inventing documents when the upstream fails.

Installation

In SourceWeft

  1. Open Knowdrift in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

knowdrift

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.

Tools

list-topics

Takes 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.

search

Retrieves the documents that best match a question inside chosen topics.

ArgumentTypeRequiredNotes
topicsarray of stringyesOne or more topic identifiers, as returned by list-topics. Only documents filed under at least one of these topics are considered.
querystringyesThe natural-language question used to rank documents by semantic relevance.
topKnumbernoHow many documents to return at most, from 1 to 30. Defaults to 10; results arrive sorted by descending relevance.

CLI usage

bash
npx @reneturcios/knowdrift list-topicsnpx @reneturcios/knowdrift search '{"topics":["technology"],"query":"How do vector databases work?","topK":5}'npx @reneturcios/knowdrift --version

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.

MCP usage

Start the stdio server with the mcp subcommand:

bash
npx -y @reneturcios/knowdrift mcp

MCP client configuration:

json
{  "mcpServers": {    "knowdrift": {      "command": "npx",      "args": ["-y", "@reneturcios/knowdrift", "mcp"]    }  }}

Docker

bash
docker run -i ghcr.io/cloudcorprecords/knowdriftdocker run --rm ghcr.io/cloudcorprecords/knowdrift search '{"topics":["technology"],"query":"What is new in quantum computing?"}'

With no arguments the container runs the stdio MCP server; any other arguments are passed to the CLI.

Configuration

VariableDefaultPurpose
DRIFLYTE_MCP_URLhttps://mcp.driflyte.com/mcpOverrides the upstream remote MCP endpoint that calls are forwarded to.
REQUEST_TIMEOUT_MS30000Per-request timeout for upstream calls, in milliseconds.

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.

Development

bash
npm installnpm run buildnpm testnpm run dev

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.

License

MIT — see LICENSE.

Source: README.md at commit 72b8bb8

Tools

2

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.

Takes no parameters.

Version history

1
  1. v0.1.0LatestNov 4, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts