<p align="center"> <img src="assets/logo.png" alt="LocalData MCP Server" width="250"> </p>

LocalData MCP Server

<!-- mcp-name: io.github.chrisgve/localdata-mcp -->

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

A single-table file — CSV, TSV, JSON, XML, INI, Parquet, Feather, Arrow — is loaded into one table named data_table, whatever the connection is called. Run describe_database(name) after connecting if you are unsure what a source exposes; multi-sheet spreadsheets and databases keep their own table names.

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.

| Tool | Description | | --- | --- | | connect_database | Open a connection to any supported database or file | | disconnect_database | Close a connection | | list_databases | List active connections | | execute_query | Run SQL with streaming, chunking, and preflight mode | | describe_database | Show schema and table list | | describe_table | Column types, indexes, row count | | find_table | Locate a table across all active connections | | analyze_query_preview | Estimate query cost before execution |

Streaming and Memory (9 tools)

| Tool | Description | | --- | --- | | next_chunk | Retrieve the next chunk of a streamed result | | request_data_chunk | Fetch a specific chunk by row range | | request_multiple_chunks | Batch-fetch multiple chunks in one call | | manage_memory_bounds | View and configure memory limits | | get_streaming_status | Check active streams and buffer usage | | clear_streaming_buffer | Free memory from a specific buffer | | get_query_metadata | Rich metadata for a completed query | | cancel_query_operation | Cancel a running or buffered query | | get_data_quality_report | Column statistics, null rates, and quality metrics |

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.

| Tool | Description | | --- | --- | | get_node / get_children | Navigate the tree | | set_node / delete_node | Create or remove nodes | | get_value / set_value / delete_key | Read and write properties | | list_keys | List key-value pairs at a node | | move_node | Relocate a node within the tree | | export_structured | Export as TOML, JSON, YAML, or Markdown |

Graph (7 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.

| Tool | Description | | --- | --- | | get_neighbors / get_edges | Traverse from a node | | add_edge / remove_edge | Manage edges | | find_path | Shortest path or all paths between two nodes | | get_graph_stats | Node/edge counts, density, DAG validation | | export_graph | Export as DOT, GML, GraphML, Mermaid, or Markdown |

Node-level operations reuse the tree tools above: get_node, set_node, delete_node, list_keys, get_value, set_value, and delete_key detect a graph connection and treat their path argument as a node ID. get_children and move_node are tree-only.

Search and Transform (2 tools)

| Tool | Description | | --- | --- | | search_data | Regex search across query results | | transform_data | Apply column transformations to result sets |

Schema and Audit (3 tools)

| Tool | Description | | --- | --- | | export_schema | Export schema as JSON Schema, Python dataclasses, TypeScript interfaces, or SQL DDL | | get_query_log | Recent query execution history | | get_error_log | Recent error log |

System (2 tools)

| Tool | Description | | --- | --- | | check_compatibility | Verify API backward compatibility | | get_metrics | Prometheus metrics text. Registered only when metrics collection is enabled, which is the default |

Data Science (12 tools)

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

| Tool | Domain | | --- | --- | | analyze_hypothesis_test | Statistical Analysis | | analyze_anova | Statistical Analysis | | analyze_effect_sizes | Statistical Analysis | | analyze_regression | Regression and Modeling | | evaluate_model_performance | Regression and Modeling | | analyze_clusters | Pattern Recognition | | detect_anomalies | Pattern Recognition | | reduce_dimensions | Pattern Recognition | | analyze_time_series | Time Series | | forecast_time_series | Time Series | | analyze_rfm | Business Intelligence | | analyze_ab_test | Business Intelligence |

Supported Data Sources

Databases

| Type | Engines | | --- | --- | | SQL | SQLite, PostgreSQL, MySQL | | SQL (analytical) | DuckDB (pip install duckdb duckdb-engine) | | SQL (enterprise) | Oracle, MS SQL Server (pip install localdata-mcp[enterprise]) | | Document | MongoDB, CouchDB (pip install localdata-mcp[modern-databases]) | | Key-value | Redis (pip install localdata-mcp[modern-databases]) | | Search | Elasticsearch (pip install localdata-mcp[modern-databases]) | | Time series | InfluxDB (pip install localdata-mcp[modern-databases]) | | Graph | Neo4j (pip install localdata-mcp[modern-databases]) | | RDF / SPARQL | Turtle (.ttl), N-Triples (.nt), remote SPARQL endpoints |

File Formats

| Category | Formats | | --- | --- | | Tabular | CSV, TSV | | Structured | JSON, YAML, TOML, XML, INI | | Spreadsheet | Excel (.xlsx, .xls), LibreOffice Calc (.ods), Apple Numbers (.numbers) | | Analytical | Parquet, Feather, Arrow, HDF5 | | Graph | DOT (Graphviz), GML, GraphML, Mermaid | | RDF | Turtle (.ttl), N-Triples (.nt) |

Multi-sheet spreadsheets are supported: each sheet becomes a separately queryable table. To load one sheet only, pass its name as the fourth argument to connect_database — connect_database("q1", "excel", "./report.xlsx", "Q1 Results"). Use "excel" for both .xlsx and .xls; "xlsx" is not a connection type.

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 and ETS forecasting; change point detection; multivariate analysis with VAR, Granger causality, and cointegration tests. forecast_time_series accepts method="arima" or method="ets"; the SARIMA and ensemble models in the domain package are not reachable through an MCP tool.

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.

Claude Code plugin

The repository doubles as a Claude Code plugin. Its manifest (.claude-plugin/plugin.json) registers the localdata MCP server via uvx localdata-mcp and ships 18 skills and 11 agents that drive the tools above. See the plugin page for how to install it and how to invoke a skill.

Upgrading from 2.0.0: graph-explore is now graph-data-explore and graph-analyst is now graph-data-analyst, and every skill moved one directory deeper. Invoking an old name silently does nothing — the changelog lists the steps.

Skills are grouped by domain under skills/:

| Group | Skills | | --- | --- | | exploration/ | explore-data, data-quality, find-reference-data | | statistical/ | hypothesis-test, ab-test, analyze-correlations, sampling-estimation | | modeling/ | regression, cluster-analysis, anomaly-detection, dimensionality-reduction, forecast, geospatial, optimization | | graph-data/ | graph-data-explore | | workflow/ | data-pipeline, research-pipeline, process-control |

Agents in agents/ take on longer analyses that span several tools:

| Agent | Scope | | --- | --- | | data-explorer | Profiles an unfamiliar dataset and reports schema, quality, and candidate analyses | | data-scientist | Composes multi-step pipelines across domains when the right approach is not obvious | | statistical-analyst | Hypothesis tests, ANOVA, effect sizes, sampling design, bootstrap estimation | | ml-analyst | Clustering, anomaly detection, dimensionality reduction, regression modeling | | forecaster | Decomposition, stationarity testing, ARIMA/E