soup-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
soup-mcp: Model Context Protocol Server for Soup
A lightweight, secure, and production-ready Model Context Protocol (MCP) server that exposes Soup's dataset intelligence and processing engine directly to AI developer tools—including Cursor, Claude Code, Antigravity, Cline, and Continue.
Why soup-mcp?
When AI engineers fine-tune local models in modern AI IDEs, data preparation is the single largest bottleneck:
Inspecting schemas and field distributions
Stripping invisible control characters, AI preambles ("As an AI language model..."), and fixing broken markdown code fences
Performing deterministic train/val/test splits with reproducible seeds
Removing duplicates and near-duplicate records
Deterministic sampling for fast testing
Merging multiple disparate data sources into a single file
Converting between Alpaca, ShareGPT, and ChatML formats
Scoring datasets for PII, toxic keywords, and educational value
soup-mcp connects these operations directly into the LLM's tool-calling loop, allowing AI assistants to prepare datasets autonomously, safely, and reproducibly.
Related MCP server: DataClinic MCP
Available MCP Tools (9 Core Tools)
Tool | Type | Description |
| Read-only | Analyzes format validity, row counts, token length distributions, empty fields, duplicates, and issues. |
| Read-only | Detects schema format ( |
| Read-only | Evaluates dataset for PII (emails/phones), toxic keywords, language distribution, and educational value. |
| Safe Mutating | Sanitizes control characters, strips AI disclaimers, repairs unclosed markdown fences, and fixes JSON syntax. |
| Safe Mutating | Drops exact and field-level duplicates with preserved row order. |
| Safe Mutating | Deterministic random subset sampling by count or percentage with seed. |
| Safe Mutating | Deterministic train/validation/test partitioning with reproducible pseudorandom seeds. |
| Safe Mutating | Lossless format conversion between Alpaca, ShareGPT, and ChatML. |
| Safe Mutating | Merges multiple JSONL dataset files into a single unified file. |
MCP Prompts (Built-in Workflow Recipes)
soup-mcp includes interactive prompts that AI assistants can load:
audit_dataset: Guides the AI to run inspection, format detection, and scoring tools to generate an exhaustive dataset health report.prepare_dataset: Guides the AI through the complete preparation recipe: inspection -> cleaning -> deduplication -> format conversion -> train/val splitting.
Security Invariants
soup-mcp adheres strictly to Soup's core security architecture:
Working Directory Containment: All read and write operations are strictly bound to the operator's Current Working Directory (
CWD). Any relative traversal (../) or absolute path escaping CWD is refused immediately.Symlink Boundary Checks: Symlinks pointing outside the workspace boundary are rejected.
Atomic File Writes: Output datasets are written to temporary files and atomically renamed (
os.replace). File generation is all-or-nothing; an interrupted operation will never corrupt an existing dataset.No In-Place Overwrites: Input datasets are never modified in place. Cleaned or converted files default to distinct filenames (e.g.
data_cleaned.jsonl).
Quickstart & Client Setup
1. Installation
git clone https://github.com/Shubham-dev-stack/soup-mcp.git
cd soup-mcp
pip install -e .2. Configuration for AI Clients
Cursor (.cursor/mcp.json or Global MCP Settings)
{
"mcpServers": {
"soup": {
"command": "python",
"args": ["-m", "soup_mcp.server"]
}
}
}Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"soup": {
"command": "python",
"args": ["-m", "soup_mcp.server"]
}
}
}Antigravity / Cline / Continue (.mcp.json)
{
"mcpServers": {
"soup": {
"command": "python",
"args": ["-m", "soup_mcp.server"]
}
}
}Testing & Verification
The test suite enforces 100% test pass rates and multi-item positive control verification:
pytest -vAll 71 tests pass covering:
Format auto-detection & inspection across multi-row datasets
Cleaning rules (invisible control characters, zero-width spaces, AI disclaimers)
De-duplication and preserved item order
Sample partitioning with deterministic seeds
Multi-dataset file merging
Split boundary checks (percentage & absolute modes with seed reproducibility)
1-to-1 message preservation during format conversion
Negative security controls (path traversal, parent symlinks, in-place overwrite prevention)
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
300+ deterministic data utilities for AI agents: validate, normalize, parse, match, redact.
Five deterministic micro-tools for AI-agent data pipelines: clean, dedupe, normalize, score, detect.
Paid deterministic data-quality and execution-verification tools for AI agents.
500+ deterministic tools for AI agents: math, conversion, validation, hashing, encoding, date/time.
Related MCP Servers
- AlicenseAqualityNot gradedmaintenanceProvides AI agents with data validation, transformation, and normalization capabilities, including JSON schema validation, CSV processing, data normalization, text cleaning, and dataset merging.566 npmMIT
- FlicenseAqualityBmaintenanceEnables AI assistants to load datasets and receive structured data-quality findings, including column classifications, missing-data summaries, and ranked issues for exploratory data analysis.2-
- AlicenseNot gradedqualityBmaintenanceEnables AI coding assistants to audit datasets against DAMA-DMBOK quality dimensions, sanitize PII, generate differential-privacy synthetic twins, compress prompt context, and export dbt schema tests and interactive HTML reports. It supports development against sensitive data with zero real records exposed to external LLMs.1MIT
- AlicenseAqualityBmaintenanceEnables AI agents to deterministically profile, clean, normalize, and validate tabular data, including locale-aware numbers, dates, text encoding, IDs, and CSV/XLSX/JSON inputs, while flagging ambiguous values instead of guessing.6176 PyPIBusiness Source 1.1