Knowz
Enables AI agents to connect to hosted Knowz vaults via MCP for knowledge management, supporting operations like search, save, browse, and amend.
README
Knowz
Knowz AI plugin for DeepSeek Harness. Product name: Knowz. Publisher: Knowz AI.
Connects agents to hosted Knowz vaults over MCP. This plugin is knowledge only. For TDD / quality gates, install KnowzCode separately — do not merge the two.
Official discovery is the GitHub topic dsh-plugin. There is no DeepSeek store.
Install
dsh plugin --profile web add github:knowz-io/deepseek-knowz-plugin
Then create a ukz_ key at https://app.knowz.io/settings/api-keys, set KNOWZ_API_KEY in the environment or $DSH_HOME/.credentials.yaml, and restart dsh web.
export KNOWZ_API_KEY=ukz_…
Do not paste API keys in chat. Do not run /knowz register on an existing Knowz account — that creates a new account. /knowz register is not the existing-user login path.
Package id: dsh-knowz.
Auth
The shipped MCP row interpolates process.env.KNOWZ_API_KEY into Authorization: Bearer. Export + restart is the path that attaches the header. $DSH_HOME/.credentials.yaml is the DSH-managed store; it is not automatically materialized into process.env.
OAuth is not in this first slice.
Personal + business tenants: two MCP rows with unique serverName values and two env refs. Same URL https://mcp.knowz.io/mcp is fine. Duplicate serverName fails at load. See MULTI-ACCOUNT.md.
MCP
Official client: @deepseek-ai/dsh-mcp-client. Hosted endpoint: https://mcp.knowz.io/mcp (HTTP JSON-RPC / streamable HTTP).
No secrets, CLIENT_ID, literal bearer token, or x-api-key in this package.
After the key is set, ask the agent to run the knowz-setup skill to map vaults.
Skills
knowz-ask, knowz-save, knowz-search, knowz-browse, knowz-amend, knowz-setup, knowz-status, knowz-flush, knowz-auto
DeepSeek Harness does not ship Cursor-style slash-command files. Ask the agent to run the skill by name.
License
MIT — publisher Knowz AI. Homepage: https://knowz.io
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.