LocalData MCP Server

LocalData MCP gives LLM agents access to local and remote data — databases, files, graphs, and structured documents — along with a full data science toolkit for analysis and modeling. It exposes 52 MCP tools across 13 database types and 20+ file formats, with memory-bounded streaming so agents can work safely on large datasets without exceeding available RAM.

Quick Start

# Install permanently
uv tool install localdata-mcp

# Or run directly without installing
uvx localdata-mcp

First-run note: Data science dependencies (scipy, scikit-learn, statsmodels, geopandas) total around 200 MB and are downloaded on first use. Subsequent starts reuse the cache. If your MCP client times out on the first launch, reconnect — the next start will be immediate.

Add to your MCP client configuration:

{
  "mcpServers": {
    "localdata": {
      "command": "localdata-mcp"
    }
  }
}

For uvx (no permanent install):

{
  "mcpServers": {
    "localdata": {
      "command": "uvx",
      "args": ["localdata-mcp"]
    }
  }
}

Then connect to any supported source and start querying:

connect_database("sales", "postgresql", "postgresql://user:pass@localhost/db")
execute_query("sales", "SELECT product, SUM(amount) FROM orders GROUP BY product")

connect_database("data", "csv", "./records.csv")
analyze_hypothesis_test("data", "SELECT amount, region FROM data", column="amount", group_column="region")

Feature Overview

Core Database (8 tools)

Connect, query, and inspect databases and files. All queries execute within configurable memory limits (default 2 GB) with automatic chunked streaming for large result sets.

Streaming and Memory (9 tools)

Tree / Structured Data (10 tools)

Navigate and edit TOML, JSON, and YAML files as navigable trees. Supports full CRUD with auto-creation of ancestor nodes and round-trip export to any supported format.

Graph (14 tools)

Work with DOT, GML, GraphML, and Mermaid files as directed multigraphs. Supports full CRUD on nodes and edges, shortest-path and all-paths queries, structural statistics, and multi-format export.

Search and Transform (2 tools)

Schema and Audit (3 tools)

System (2 tools)

Data Science (12 tools)

Run statistical analysis, modeling, and pattern detection directly on query results from any connected source.

Supported Data Sources

Databases

File Formats

Multi-sheet spreadsheets are fully supported: each sheet becomes a separately queryable table. Connect to a specific sheet with ?sheet=SheetName in the path.

Data Science Domains

Statistical Analysis — t-tests, chi-squared, Mann-Whitney, Kruskal-Wallis, and related hypothesis tests; one-way ANOVA with post-hoc tests; Cohen's d, eta-squared, and other effect size measures.

Regression and Modeling — linear, polynomial, logistic, ridge, lasso, and elastic net regression; model evaluation with R², RMSE, MAE, and classification metrics; automated feature selection.

Pattern Recognition — K-means, DBSCAN, and hierarchical clustering; anomaly detection via isolation forest, LOF, and one-class SVM; dimensionality reduction with PCA, t-SNE, and UMAP.

Time Series — decomposition, stationarity testing, autocorrelation analysis; ARIMA, SARIMA, and ETS forecasting; change point detection; multivariate analysis with VAR, Granger causality, and cointegration tests.

Business Intelligence — A/B test statistical analysis; RFM customer segmentation; cohort analysis, CLV modeling, and funnel analysis.

Geospatial — distance and coordinate calculations, spatial joins, interpolation, and network analysis.

Optimization — linear programming, constrained optimization, assignment problems, and network optimization.

Sampling and Estimation — bootstrap confidence intervals, Bayesian estimation, Monte Carlo simulation, and stratified sampling.

Architecture

• Intention-driven interface — tools accept semantic parameters ("find strong correlations") rather than requiring statistical procedure names or threshold values
• Progressive disclosure — simple calls return high-level insights with sensible defaults; advanced parameters are available when needed
• Streaming-first execution — all operations are designed for chunked processing; tools automatically switch strategies based on data size, keeping memory usage within configured bounds
• Composition metadata — every tool result includes metadata that downstream tools can use directly, enabling chained analysis without manual wiring

Configuration

LocalData MCP uses environment variables for optional settings. The defaults work for most cases.

Set in your MCP server configuration under "env", or in a .env file in the working directory.

Documentation

• Database Connection Guide — connection strings, driver setup, and security practices
• Docker Usage Guide — container deployment and configuration
• Advanced Examples — production-ready usage patterns
• Troubleshooting Guide — common issues and solutions
• FAQ — frequently asked questions
• API Reference — full tool and parameter reference

Development

git clone https://github.com/ChrisGVE/localdata-mcp.git
cd localdata-mcp
uv sync --all-extras
uv run pytest

The test suite includes 1,600+ unit tests, 234+ integration tests, and 62 enterprise-scale tests across 7 database types with 100K rows each.

Contributing

Contributions are welcome. Please read CONTRIBUTING.md before submitting a pull request.

License

MIT — see LICENSE for details.