TransForm MCP Server
Enables dynamic format selection (JSON, Parquet, Arrow IPC) for MCP tool outputs, with a Java Spring Boot server and Python client for agentic data systems.
README
TransForm: Dynamic Format Selection for MCP Tool Outputs
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
Layout
| 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) |
Java server
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.jar
MCP endpoint: http://localhost:8000/mcp/mcp
Optional BIRD SQLite: set BIRD_SQLITE_ROOT to the dev database directory.
Python client
pip install -r requirements.txt
export MCP_URL=http://localhost:8000/mcp/mcp
export SERVER_URL=http://localhost:8000
python -m client.mcp_client
Paper
cd novas-workshop && latexmk -pdf main.tex
Figures are in novas-workshop/figures/. Regenerate selection diagrams with figures/render_selection_figures.sh (requires mermaid-cli).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.