Correct the tape and packaging claims in the hiberden-mcp entry

Tape led the coverage list uncaveated. It is beta and is not currently
validated on physical hardware, so it now says that and sits last.

The entry paired the Linux marker with "Ships as a signed Desktop Extension
(MCPB)", which together imply a Linux MCPB. There isn't one: the bundle carries
a Windows binary and declares platforms ["win32"]. Linux support is real but
arrives as a standalone connector binary, so the two are now stated separately.

README.md

@@ -1530,7 +1530,7 @@ Provides direct access to local file systems with configurable permissions. Enab
 
 - [8b-is/smart-tree](https://github.com/8b-is/smart-tree) 🦀 🏠 🍎 🪟 🐧 - AI-native directory visualization with semantic analysis, ultra-compressed formats for AI consumption, and 10x token reduction. Supports quantum-semantic mode with intelligent file categorization.
 - [aadilr/changethisfile-mcp](https://github.com/aadilr/changethisfile-mcp) [![aadilr/changethisfile-mcp MCP server](https://glama.ai/mcp/servers/aadilr/changethisfile-mcp/badges/score.svg)](https://glama.ai/mcp/servers/aadilr/changethisfile-mcp) 📇 ☁️ - Free file conversion between 690+ formats. Tools: `convert_file` (URL or base64 in → signed download URL out) and `list_conversions`. Covers image, video, audio, document, data, font, ebook, and archive formats. No auth or signup required; remote streamable-HTTP endpoint available (see README).
-- [Agaveis/hiberden-mcp](https://github.com/Agaveis/hiberden-mcp) [![Agaveis/hiberden-mcp MCP server](https://glama.ai/mcp/servers/Agaveis/hiberden-mcp/badges/score.svg)](https://glama.ai/mcp/servers/Agaveis/hiberden-mcp) 🦀 🏠 🪟 🐧 - Read and verify your local media-archive catalog from an AI assistant: 3-2-1 coverage across LTO tape, disk, NAS, and S3-compatible cloud. Verifies a copy by physically reading it back and re-hashing it against the source; catalog-management and delete tools are off by default. Ships as a signed Desktop Extension (MCPB).
+- [Agaveis/hiberden-mcp](https://github.com/Agaveis/hiberden-mcp) [![Agaveis/hiberden-mcp MCP server](https://glama.ai/mcp/servers/Agaveis/hiberden-mcp/badges/score.svg)](https://glama.ai/mcp/servers/Agaveis/hiberden-mcp) 🦀 🏠 🪟 🐧 - Read and verify your local media-archive catalog from an AI assistant: 3-2-1 coverage across disk, NAS, S3-compatible cloud, and LTO tape (tape is beta and not validated on physical hardware). Verifies a copy by physically reading it back and re-hashing it against the source; catalog-management and delete tools are off by default. On Windows it installs as a signed Desktop Extension (MCPB); on Linux the same connector ships as a standalone binary.
 - [box/mcp-server-box-remote](https://github.com/box/mcp-server-box-remote/) 🎖️ ☁️ - The Box MCP server allows third party AI agents to securely and seamlessly access Box content and use tools such as search, asking questions from files and folders, and data extraction.
 - [bzsanti/oxidize-python](https://github.com/bzsanti/oxidize-python) [![bzsanti/oxidize-python MCP server](https://glama.ai/mcp/servers/bzsanti/oxidize-python/badges/score.svg)](https://glama.ai/mcp/servers/bzsanti/oxidize-python) 🐍 🏠 🍎 🪟 🐧 - Rust-powered PDF toolkit: create, read, and analyze PDFs; extract text and entities for RAG; convert to Markdown; split, merge, rotate, and reorder pages; add content, annotations, and form fields; and encrypt documents. Ships in the `oxidize-pdf` PyPI package — run locally with `uvx oxidize-mcp`.
 - [ckanthony/Chisel](https://github.com/ckanthony/Chisel) [![chisel MCP server](https://glama.ai/mcp/servers/@ckanthony/chisel/badges/score.svg)](https://glama.ai/mcp/servers/@ckanthony/chisel) 🦀 🏠 🍎 🐧 ☁️ - Reduce context usage on file use. Send only unified diffs instead of full files (up to 20-100× fewer tokens), and read large files with targeted `grep`/`sed` instead of full reads (up to 500×). Kernel-enforced path confinement hard-locks the agent to a configured root: no accidental reads or writes outside scope. Standalone for your file access or embed in any MCP server (Rust, Node.js, Python via WASM).