MCP server that lets any AI agent control WorldBox via the WorldBoxBridge BepInEx mod.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"worldbox-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# worldbox-mcp (Python MCP server) The Python half of [worldbox-mcp](https://github.com/fullya99/worldbox-mcp). Distributed on PyPI. ```bash uvx worldbox-mcp # stdio transport (default) uvx worldbox-mcp --http # Streamable HTTP transport uvx worldbox-mcp --help ``` See the [top-level README](../README.md) and the [docs site](https://fullya99.github.io/worldbox-mcp/) for full installation instructions and client configuration recipes. ## Development ```bash uv sync --all-extras uv run pytest uv run ruff check . uv run mypy --strict src ``` ## Architecture This package is a thin, typed façade over the [`WorldBoxBridge`](../mod) HTTP API. It: 1. Speaks the [MCP protocol](https://modelcontextprotocol.io) to AI clients. 2. Validates tool inputs with Pydantic. 3. Translates each MCP `tools/call` into a `POST /cmd` request against the local mod. 4. Maps bridge error codes to MCP errors with full preservation of detail (no swallowing). See [`docs/architecture.md`](../docs/architecture.md) for the full picture.
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.