Transform — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Transform (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Research artifact for the NOVAS workshop paper: a control/data-plane split for MCP tabular tool results with dynamic format selection (JSON, Parquet, Arrow IPC).
Artifact: https://github.com/shashank524/TransForm
| Path | Description |
|---|---|
novas-workshop/ | Workshop paper (main.tex, ref.bib, figures) |
java-server/ | Java (Spring Boot) MCP server with fused format selection |
java-sdk/ | Vendored MCP Java SDK |
client/ | Python MCP client (pip install mcp) |
mvn -f pom.xml package -DskipTests -pl java-server -am
java --add-opens=java.base/java.nio=ALL-UNNAMED \
-jar java-server/target/multimodal-mcp-0.1.0-SNAPSHOT.jarMCP endpoint: http://localhost:8000/mcp/mcp
Optional BIRD SQLite: set BIRD_SQLITE_ROOT to the dev database directory.
pip install -r requirements.txt
export MCP_URL=http://localhost:8000/mcp/mcp
export SERVER_URL=http://localhost:8000
python -m client.mcp_clientcd novas-workshop && latexmk -pdf main.texFigures are in novas-workshop/figures/. Regenerate selection diagrams with figures/render_selection_figures.sh (requires mermaid-cli).
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.