Local MCP server for vibe-sunsang analysis workflows.
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":"vibe-sunsang-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.
# vibe-sunsang-mcp Local MCP server for `vibe-sunsang` session analysis, mentoring context, and report generation. ## Install Published package: - [PyPI: `vibe-sunsang-mcp`](https://pypi.org/project/vibe-sunsang-mcp/0.1.3/) ```bash uvx vibe-sunsang-mcp install ``` Or install it into a local environment: ```bash pip install vibe-sunsang-mcp ``` The installer writes: - project `.mcp.json` for Claude-compatible local MCP registration - project `.gemini/settings.json` - project `gemini.md` - project `AGENTS.md` - home `~/.codex/config.toml` ## Run ```bash vibe-sunsang-mcp ``` ## CLI Helpers ```bash python -m vibe_sunsang_mcp archive-logs --platform all --mode incremental python -m vibe_sunsang_mcp analyze-session --session-id claude-xxxxxxxxxxxx python -m vibe_sunsang_mcp get-mentoring --session-id claude-xxxxxxxxxxxx python -m vibe_sunsang_mcp generate-report --platform all python -m vibe_sunsang_mcp generate-report --platform all --compare-with 2026-04-01T00:00:00Z python -m vibe_sunsang_mcp generate-gold-set --labels-dir tests/gold-set ``` These commands call the same underlying tool implementations as the MCP server, but are useful for local archiving, gold set preparation, and smoke testing without opening a client. ## MCP Tools - `archive_logs` - `analyze_session` - `get_mentoring` - `generate_report` ## Development ```bash python -m pytest python -m ruff check src tests ``` ## Gold Set ```bash python -m vibe_sunsang_mcp evaluate-gold-set \ --labels-dir tests/gold-set \ --archive-root ~/vibe-sunsang ``` This compares archived sessions against human-labeled files in `tests/gold-set/`. ## Scope Supported platforms: - Claude Code - Gemini CLI - Codex CLI
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.