by lyc403223157-source · MCP Server · ★ 49
Knowledge Inbox English | 简体中文 Harness-neutral, local-first knowledge ingestion for Obsidian and other local retrieval tools. It turns links, text, videos, screenshots, PDFs, and local files into structured Markdown knowledge cards. Hermes, Codex, OpenClaw, and other MCP clients share the same adapters and processing service. Current release: . Web and file ingestion run cross-platform. WeChat Channels downloading is an optional, experimental macOS integration that requires the desktop WeChat client and a local TLS proxy. How it works Every source is normalized into a .
| Stars | 49 |
| Forks | 0 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 58.2127367244563/100 |
| Last Updated | 2026-08-12 |
| Created | 2026-08-11 |
| Platforms | mcp, python |
| Est. Tokens | ~9k |
These tools work well together with knowledge-inbox for enhanced workflows:
Explore other popular mcp server tools:
knowledge-inbox is Local-first knowledge ingestion for AI agents and Obsidian. It is categorized as a MCP Server with 49 GitHub stars.
knowledge-inbox is primarily written in Python. It covers topics such as fastapi, hermes-agent, knowledge-management.
You can find installation instructions and usage details in the knowledge-inbox GitHub repository at github.com/lyc403223157-source/knowledge-inbox. The project has 49 stars and 0 forks, indicating an active community.
knowledge-inbox is released under the Apache-2.0 license, making it free to use and modify according to the license terms.