Skip to main content
Glama
README.md
# hybridforgelab-unfold-mcp: moved to bytestay-unfold-mcp

This package has moved to **[bytestay-unfold-mcp](https://pypi.org/project/bytestay-unfold-mcp/)**. Hybrid Forge Lab is now ByteStay.

This last version only installs bytestay-unfold-mcp and forwards to it. It prints a one-line notice on stderr and gets no more updates.

## Switch

Replace `hybridforgelab-unfold-mcp` with `bytestay-unfold-mcp` in your MCP client config:

```json
"command": "uvx",
"args": ["--from", "bytestay-unfold-mcp", "unfold-mcp"]
```

Or with Claude Code:

```bash
claude mcp add unfold --env RAPIDAPI_KEY=your-rapidapi-key -- uvx --from bytestay-unfold-mcp unfold-mcp
```

The environment variables are the same, so your keys keep working.

## Links

- Package: [bytestay-unfold-mcp](https://pypi.org/project/bytestay-unfold-mcp/)
- Source: [Bytestay/unfold-mcp](https://github.com/Bytestay/unfold-mcp)
- Unfold API: [unfold.bytestay.pt](https://unfold.bytestay.pt)

TDQS

A3.8/5.0

Scored across 1 tool

Disambiguation5/5

There is only one tool, so there is no possibility of misselection or overlapping purpose. The single tool's purpose (document to Markdown conversion) is unambiguous.

Naming Consistency5/5

The lone name, convert_document, follows a clean verb_noun snake_case pattern. With a single tool there is no convention mixing to worry about.

Tool Count3/5

One tool is exactly on-scope for a narrow conversion server, but the surface feels thin—there's no batch option or format-discovery endpoint to round it out. Acceptable for its stated purpose but minimal.

Completeness4/5

The core lifecycle (take a URL or path, emit Markdown with auto-detected format) is fully covered, so an agent won't hit a dead end for the primary workflow. Minor gaps exist: no batch conversion and no way to list supported formats or output options.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues