serbian-data-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@serbian-data-mcp Search datasets about population in Serbia"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Serbian Data MCP Server
MCP server for accessing Serbian open data portal (data.gov.rs) with built-in visualization, storytelling, and analytics capabilities.
pip install serbian-data-mcpFeatures
Data Access
π Search 3,400+ datasets from Serbian government (data.gov.rs)
π₯ Download data in JSON, CSV, XML, XLSX formats
π·πΈ Full Serbian language support (UTF-8)
π Built-in rate limiting and caching
Visualization β 15+ Chart Types
π Basic charts: line, bar, pie, scatter, histogram, box plot
πΊοΈ Maps: choropleth (25 Serbian districts), bubble map, multi-layer map
π Data journalism: slope chart, waffle chart, population pyramid, sankey diagram, radar chart
π― Advanced: heatmap, treemap, gauge/donut, funnel, sparklines, animated timelines
β¨ Special: arrow chart, dumbbell chart, lollipop chart
Storytelling & Analytics
π° Infographics: big number cards, auto-generated insights, timeline ribbon, data tables
π Dashboards: multi-panel layouts with mixed chart types
π Scrollytelling: scroll-driven HTML stories with IntersectionObserver
π Forecasting: linear/exponential projections with RΒ² and growth rates
π Benchmarking: compare against EU averages or custom references
π Cross-dataset analysis: correlations, outliers, rank divergences
Export & Sharing
π HTML: styled, responsive pages with dark data-journalism aesthetic
πΌοΈ PNG/PDF: export with kaleido (graceful fallback if not installed)
π Embed: iframe embed code for websites/blogs
π JSON: raw Plotly spec for custom integration
Data Tools
π§ Transformation tools: filter, group, aggregate, sort, select
π Auto-extracted insights: extremes, temporal changes, rankings, outliers
π¬ Auto-generated narrative summaries
π§ Git repository visualization and analysis
Related MCP server: opendata-ua-mcp
π Quick Start
Install from PyPI (Recommended)
pip install serbian-data-mcpThen add to your MCP client configuration (see Usage below).
Install from Smithery
Smithery is a registry and CLI for discovering and installing MCP servers.
# Install the Smithery CLI
npm install -g smithery@latest
# Add to Claude Desktop
smithery mcp add acailic/serbian-data-mcp --client claude
# Add to Cursor
smithery mcp add acailic/serbian-data-mcp --client cursor
# Or connect as a remote Smithery connection
smithery mcp add acailic/serbian-data-mcp --id serbian-dataNote: Requires Node.js 20+. After adding, restart your AI client for changes to take effect.
Install from Source
git clone https://github.com/acailic/serbian-data-mcp
cd serbian-data-mcp
uv syncπ Configuration
The server works out of the box with sensible defaults. To customize, create a config.json in your working directory (or next to the installed package):
{
"api_base": "https://data.gov.rs",
"rate_limit": 1.0,
"timeout": 30,
"cache_dir": ".cache",
"export_dir": "exports"
}See config.example.json in the source repo for all options.
π Usage
Claude Desktop Configuration
{
"mcpServers": {
"serbian-data": {
"command": "serbian-data-mcp"
}
}
}Or if you installed from source:
{
"mcpServers": {
"serbian-data": {
"command": "python",
"args": ["-m", "serbian_data_mcp"]
}
}
}Via Smithery CLI
If you installed via Smithery, the configuration is handled automatically. Just run:
# For Claude Desktop
smithery mcp add acailic/serbian-data-mcp --client claude
# For Cursor
smithery mcp add acailic/serbian-data-mcp --client cursorThen restart your AI client. No manual config editing needed.
π Visualization Gallery
All charts feature a polished dark data-journalism theme with Inter font, refined hover styles, and consistent Serbian flag color palette. Three themes available: dark, light, and infographic.
Line Charts β Time Series & Trends

Bar Charts β Comparisons & Rankings

Choropleth Map β Serbian Districts
Interactive map of 25 Serbian districts with Cyrillic/Latin name resolution, available as choropleth or bubble map.
Population Pyramid β Demographics

Slope Chart β Ranking Changes
Shows how district rankings shifted between censuses (2002 β 2022), with green for gainers and red for losers.
Sankey Diagram β Budget Flows
Visualize budget flows from revenue sources through ministries to spending categories.
Radar Chart β Multi-Metric Comparison
Compare cities across population, GDP per capita, schools, hospitals, and parks on a single spider plot.
Waffle Chart β Proportional Data
"1 in 4 Serbs live in Belgrade" β each category gets a block of squares in a 10Γ10 grid.
Donut Charts β Sector Distribution

Infographics β Data Stories
Auto-generated single-page stories with big number cards, timeline ribbon, insights, and supporting charts.
Dashboards β Multi-Panel Views
Combine multiple chart types into a single dashboard layout with big number KPIs.
Scrollytelling β Scroll-Driven Stories
Interactive HTML stories that reveal data as the user scrolls, with IntersectionObserver animations.
Examples
Search & Visualize
# Search datasets
datasets = await mcp.call_tool("search_datasets", {
"query": "population",
"format": "json",
"page_size": 10
})
# Create a basic chart
chart = await mcp.call_tool("create_visualization", {
"data": data,
"chart_type": "line",
"title": "Population Trends",
"x_column": "year",
"y_column": "population",
})
# Create an advanced chart (slope chart for census changes)
slope = await mcp.call_tool("create_slope_chart", {
"data": census_data,
"entity_column": "district",
"start_column": "pop_2002",
"end_column": "pop_2022",
"title": "Census Ranking Changes 2002β2022"
})Forecast & Benchmark
# Forecast future GDP
forecast = await mcp.call_tool("forecast_data", {
"data": gdp_data,
"time_column": "year",
"value_column": "gdp",
"periods_ahead": 5
})
# Compare against benchmarks
comparison = await mcp.call_tool("benchmark_data", {
"data": city_data,
"value_column": "gdp_pc",
"entity_column": "city",
"benchmarks": {"EU average": 35000}
})Create a Full Infographic
story = await mcp.call_tool("create_infographic", {
"data": population_data,
"title": "Srbija po Popisu 2022",
"chart_type": "bar",
"x_column": "district",
"y_column": "population_2022",
"extra_big_numbers": [
{"number": "6.6M", "label": "Ukupno stanovnika", "color": "gold", "trend": "down"},
{"number": "23%", "label": "Beograd region", "color": "blue", "trend": "up"},
],
"timeline_events": [
{"year": "2002", "label": "Popis 2002", "dot_class": ""},
{"year": "2022", "label": "Popis 2022", "dot_class": "gold"},
]
})Available MCP Tools
Data Access
Tool | Description |
| Search 3,400+ datasets with filters |
| Get complete dataset details |
| Download and parse resource data |
| Browse data providers |
| Autocomplete for search |
Data Transformation
Tool | Description |
| Filter rows by conditions |
| Group and aggregate |
| Sort by column(s) |
| Select/rename columns |
| Statistical summary of dataset |
Basic Charts
Tool | Description |
| Line, bar, pie, scatter, histogram, box plot |
| Heatmap, treemap, gauge, funnel, sparklines, animated |
| Directional arrow chart |
| Before/after comparison |
Novel Charts
Tool | Description |
| Ranking changes between two periods |
| Proportional icon grid |
| Age Γ sex demographic distribution |
| Budget/energy flow visualization |
| Multi-metric spider comparison |
Maps
Tool | Description |
| Colored district map of Serbia |
| Bubble-sized district map |
| Toggle between indicators |
Analytics & Forecasting
Tool | Description |
| Linear/exponential projections |
| Compare against reference values |
| Cross-dataset correlations |
Storytelling
Tool | Description |
| Full data story with KPIs, timeline, chart, insights |
| Multi-panel dashboard layout |
| Scroll-driven interactive story |
Export & Sharing
Tool | Description |
| Export as HTML, JSON, PNG, or PDF |
| Generate iframe embed code |
| Add rich contextual tooltips |
π Documentation
Quick Start Guide β Get started in 5 minutes
Usage Examples β 24+ real-world examples and use cases
API Reference β Complete tool documentation with parameters
Troubleshooting β Common issues and solutions
Contributing Guide β Developer contribution guidelines
Development
Setup Development Environment
make installGenerate Showcase Exports
uv run python generate_showcase.pyThis creates 12 polished HTML files in exports/ demonstrating all chart types with sample Serbian data.
Running Tests
make test # Run all tests with coverage
make test-quick # Quick tests (no coverage)Code Quality Checks
make check # Run all quality checks (lint, format, type-check, security)
make check-quick # Quick checks (lint + format only)Project Structure
serbian-data-mcp/
βββ exports/ # Generated HTML visualizations
βββ src/serbian_data_mcp/
β βββ api/ # API client for data.gov.rs
β βββ catalog/ # Dataset catalog and search
β βββ data/ # Data parsing and transformation
β βββ intelligence/ # Query expansion and smart search
β βββ viz/
β β βββ charts.py # Basic 6 chart types (auto-themed)
β β βββ advanced_charts.py # Heatmap, treemap, gauge, funnel, sparklines
β β βββ novel_charts.py # Slope, waffle, pyramid, sankey, radar
β β βββ maps.py # Choropleth map of 25 Serbian districts
β β βββ map_advanced.py # Bubble map, multi-layer map
β β βββ infographics.py # Full infographic builder
β β βββ scrollytelling.py # Scroll-driven HTML stories
β β βββ animations.py # Animated charts (timeline, bars, comparison)
β β βββ themes.py # Dark/light/infographic themes
β β βββ insights.py # Auto-extracted insights & narratives
β β βββ tooltips.py # Rich hover tooltips
β β βββ forecast.py # Linear/exponential forecasting
β β βββ data_tables.py # Styled data tables
β β βββ special_charts.py # Arrow, dumbbell, lollipop
β β βββ exporters.py # HTML/PNG/JSON/PDF/export
β β βββ datawrapper_export.py # Datawrapper cloud API
β βββ config.py # Configuration management
β βββ exceptions.py # Custom exceptions
β βββ tools.py # MCP tool definitions (30+ tools)
βββ tests/ # Comprehensive test suite (314 tests)
βββ generate_showcase.py # Generate showcase HTML exports
βββ .github/workflows/ # CI/CD configuration
βββ pyproject.toml # Project configuration
βββ Makefile # Development commandsLicense
MIT License - see LICENSE file
Available Tools
67 toolsadd_chart_annotationC
Add a callout annotation to a chart for storytelling.
Text box with optional arrow pointing to a data point.
Inputs: text (required), figure (required), x, y, +3 more. Returns: object
add_chart_calloutsA
Add multiple annotation callout boxes to highlight data points.
Each box has arrow pointing to data. Points: {x, y, text, color?, ax?, ay?}
Returns: Enhanced figure dict
Inputs: figure (required), points (required), prefix, suffix. Returns: object
add_chart_highlight_zoneA
Add a shaded vertical highlight zone to a chart.
Highlights a time period with a colored band. Ideal for: COVID years, crisis periods, policy changes.
Returns: Enhanced figure dict
Inputs: x_end (required), figure (required), x_start (required), fill_color, +1 more. Returns: object
add_chart_threshold_lineB
Add a horizontal threshold/reference line with label.
Ideal for: EU average benchmark, target/goal line, critical threshold.
Returns: Enhanced figure dict
Inputs: figure (required), threshold (required), color, label, +1 more. Returns: object
aggregate_data_toolA
Aggregate a single column using a function.
Shorthand for transform_data(operation='aggregate'). Returns the scalar result as {"value": ..., "column": ..., "function": ...}.
Functions: sum, mean, median, min, max, count, std, var.
Inputs: data (required), column (required), function. Returns: object
apply_chart_themeA
Apply visual theme to a chart figure from create_chart().
Themes: 'dark' (data-journalism), 'light' (clean), 'infographic' (large type). Add annotations: [{"text": "...", "x": val, "y": val}] for callouts. Add zones: [{"x_start": val, "x_end": val, "label": "..."}] for highlights.
Inputs: figure (required), theme, annotations, highlight_zones. Returns: object
benchmark_dataB
Compare against benchmarks (EU average, regional, custom).
Returns: {statistical_benchmarks, best_performer, worst_performer, comparisons, insights}
Inputs: data (required), value_column (required), entity_column (required), benchmarks. Returns: object
browse_recent_datasetsA
Discover newly added/updated datasets. Returns most recently modified first.
Inputs: days, page_size. Returns: object
build_dashboardB
Build multi-panel dashboard HTML. Each panel: chart, HTML, or big number.
Inputs: panels (required), title, filename. Returns: object
build_infographicA
Create a complete infographic HTML: headline + big number + chart + insights.
Self-contained HTML with responsive design. Opens in any browser. Saved to exports/ directory.
Returns: {filepath, metadata, insights, headline}
Inputs: data (required), theme, title, filename, +5 more. Returns: object
compare_cross_datasetA
Extract insights by comparing two related datasets.
Finds correlations, divergences, and rank disagreements. Ideal for: 'population vs air quality' analyses.
Returns: {summary_a, summary_b, correlation, insights}
Inputs: data_a (required), data_b (required), value_column_a (required), value_column_b (required), +4 more. Returns: object
compare_datasetsB
Compare two datasets side by side. Helps choose the best dataset for analysis.
Shows differences in publisher, tags, resource count, formats, quality.
Inputs: dataset_id_1 (required), dataset_id_2 (required). Returns: object
compute_metricsA
Compute derived metrics: YoY changes, per-capita, growth rates, index (base=100).
Returns: {yoy_changes, per_capita, growth_rates, index_values, derived_data}
Inputs: data (required), time_column, entity_column, population_column. Returns: object
create_animated_chartC
Create animated charts with smooth transitions and play/pause.
Inputs: data, theme, title, datasets, +5 more. Returns: object
create_arrow_chartA
Arrow-style chart showing directional changes. Green=positive, red=negative.
Ideal for: rankings change, budget surplus/deficit, growth/decline.
Returns: {filepath, title, rows}
Inputs: data (required), label_column (required), value_column (required), theme, +3 more. Returns: object
create_bubble_mapA
Bubble map of Serbia β circle size = magnitude. Avoids large-district bias.
Returns: {filepath, districts_matched, title}
Inputs: data (required), name_column (required), value_column (required), theme, +2 more. Returns: object
create_chartA
Create interactive charts from data. Supports 20+ chart types.
BASIC CHARTS (most common):
"line": x_column + y_column β time series, trends
"bar": x_column + y_column β comparisons, rankings
"pie": values_column + names_column β proportions
"scatter": x_column + y_column β correlations
"histogram": x_column or y_column β frequency distributions
"box": y_column (+ optional x_column) β statistical distributions
Inputs: data (required), bins, fill, label, +37 more. Returns: object
create_cone_3dA
Interactive 3D vector field / quiver plot (WebGL, orbit-able).
Renders a cone at each (x, y, z) anchor pointing along the vector (u, v, w) β a 3D arrow field of direction + magnitude. Cones are colored by vector magnitude and sized by sizeref. Distinct from the scalar 3D charts: a cone field encodes a vector (flow, gradient, force) at each sample point.
Ideal for: wind / air-flow fields, magnetic or electric fields, fluid-flow simulations, gradient directions across a 3D domain.
Returns: {filepath, title, rows}
Inputs: data (required), u_column (required), v_column (required), w_column (required), +10 more. Returns: object
create_data_tableA
Create a styled, responsive HTML data table with conditional formatting.
Professional table with ranking indicators and value formatting. Highlights max or min value row.
Ideal for: district statistics, budget breakdowns, top-N listings.
Returns: {filepath, title, rows, total_rows, columns}
Inputs: data (required), title, caption, columns, +5 more. Returns: object
create_dumbbell_chartA
Dumbbell chart: before/after comparison with connected dots.
Green=increase, red=decrease. Shows magnitude and direction.
Ideal for: population 2010 vs 2022, budget planned vs executed.
Returns: {filepath, title, rows}
Inputs: data (required), end_column (required), label_column (required), start_column (required), +3 more. Returns: object
create_isosurface_3dA
Interactive 3D iso-surface from a volumetric scalar field (WebGL, orbit-able).
Renders the 3D boundary where value_column falls within [isomin, isomax] β
a level set of a continuous fourth variable sampled across (x, y, z). The
marching-cubes extraction runs client-side at render, so scattered samples
are accepted without a regular grid or SciPy.
Ideal for: pollution/concentration thresholds across a 3D monitoring volume, isotherms, groundwater head surfaces, any "region where value β₯ threshold".
Returns: {filepath, title, rows}
Inputs: data (required), x_column (required), y_column (required), z_column (required), +8 more. Returns: object
create_line_3dA
Interactive 3D line / trajectory chart (WebGL, orbit-able).
Connects points through 3-space β a trajectory. Split into one line per category via color_column.
Ideal for: a route through lat/lon/altitude, a metric evolving across region Γ time, multi-decade demographic trajectories.
Returns: {filepath, title, rows}
Inputs: data (required), x_column (required), y_column (required), z_column (required), +4 more. Returns: object
create_lollipop_chartA
Lollipop chart β dots on stems for clean ranking. Can highlight one entity.
Ideal for: district population ranking, budget by ministry, top-N lists.
Returns: {filepath, title, rows}
Inputs: data (required), label_column (required), value_column (required), theme, +4 more. Returns: object
create_mesh_3dA
Interactive 3D mesh from scattered points (WebGL, orbit-able).
Triangulates scattered (x, y, z) points into a connected surface or
enclosing hull β unlike create_surface_3d which needs a regular grid.
An optional intensity_column colors each vertex by a fourth metric.
Ideal for: irregular terrain/field point clouds, region bounding shapes, sparse 3D samples (e.g. pollution at uneven monitoring stations).
Returns: {filepath, title, rows}
Inputs: data (required), x_column (required), y_column (required), z_column (required), +7 more. Returns: object
create_multi_layer_mapA
Multi-layer choropleth with toggle buttons between indicators.
Each layer: {data, name_column, value_column, label, colorscale}
Returns: {filepath, layer_count, title}
Inputs: layers (required), theme, title, filename. Returns: object
create_population_pyramidA
Population pyramid: age Γ sex distribution. Males left, females right.
Essential for census data from RZS. Classic demographic visualization.
Returns: {filepath, title, age_groups}
Inputs: data (required), age_column (required), male_column (required), female_column (required), +3 more. Returns: object
create_radar_chartA
Radar/spider chart for multi-metric comparison.
Compare entities across multiple indicators on one radar plot.
Ideal for: comparing districts on population+budget+schools+hospitals+air quality.
Returns: {filepath, title, entities, metrics}
Inputs: data (required), value_columns (required), category_column (required), theme, +2 more. Returns: object
create_sankey_diagramA
Sankey (alluvial) diagram showing flow between categories.
Ideal for: budget flow (revenueβministryβspending), energy distribution, migration flows, supply chains.
Returns: {filepath, title, flows}
Inputs: data (required), value_column (required), source_column (required), target_column (required), +3 more. Returns: object
create_scatter_3dA
Interactive 3D scatter / bubble chart (WebGL, orbit-able).
Plots three numeric dimensions as points in 3-space, with optional color, bubble size, and marker shape encoding up to three more variables.
Ideal for: spatial data (lat/lon/altitude), district Γ year Γ population, exploring three census indicators at once.
Returns: {filepath, title, rows}
Inputs: data (required), x_column (required), y_column (required), z_column (required), +6 more. Returns: object
create_scrollytelling_storyA
Create a scroll-driven HTML data story (scrollytelling).
Multi-section page with narrative text scrolling left and interactive charts updating right β the visualise.admin.ch pattern.
Inputs: steps (required), theme, title, byline, +2 more. Returns: object
create_serbia_mapA
Choropleth map of Serbia by 25 administrative districts. Color-coded by metric.
District names in Natural Earth format (English transliteration). Cyrillic and city shorthand also supported (e.g., 'NiΕ‘', 'Novi Sad'). Use list_serbia_districts() to see all recognized names.
Returns: {filepath, districts_matched, total_districts, title}
Inputs: data (required), name_column (required), value_column (required), theme, +3 more. Returns: object
create_slope_chartA
Slope chart: ranking changes between two periods with connecting lines.
Green=gained rank, red=lost rank.
Ideal for: census ranking 2002β2022, budget share shifts, district reorderings.
Returns: {filepath, title, rows}
Inputs: data (required), end_column (required), start_column (required), entity_column (required), +4 more. Returns: object
create_streamtube_3dA
Interactive 3D streamtube plot of a vector field's flow (WebGL, orbit-able).
Integrates the (u, v, w) vector field into streamlines rendered as tubes
whose diameter encodes local flow magnitude. Distinct from
create_cone_3d (one discrete arrow per sample): a streamtube shows the
integrated trajectories β wind corridors, ocean currents, magnetic field
lines β rather than the instantaneous direction at each point. The
streamline integration runs client-side at render, so a sampled grid needs
no SciPy or iterative solver.
Ideal for: wind / ocean circulation, ventilation or HVAC airflow, magnetic / electric field lines, any continuous flow domain where the path of the flow matters more than the per-point arrow.
Returns: {filepath, title, rows}
Inputs: data (required), u_column (required), v_column (required), w_column (required), +8 more. Returns: object
create_surface_3dA
Interactive 3D surface (landscape) chart from gridded data (WebGL, orbit-able).
Long-format (x, y, z) rows are pivoted into a z-value grid and rendered as a continuous surface. Suited to elevation, density, or any scalar field sampled on a regular grid.
Ideal for: temperature/air-quality across city Γ month, terrain surfaces, optimization landscapes.
Returns: {filepath, title, rows}
Inputs: data (required), x_column (required), y_column (required), z_column (required), +4 more. Returns: object
create_volume_3dA
Interactive 3D volume render of a volumetric scalar field (WebGL, orbit-able).
Renders the full semi-transparent scalar field across (x, y, z) β a
see-through cloud whose density + color encode value_column, with a
configurable number of internal iso-surfaces. Distinct from
create_isosurface_3d (which draws only the single boundary where value
equals a threshold): a volume shows the interior distribution of the field,
not just its level-set shell. The ray-marched rendering runs client-side, so
scattered samples are accepted without a regular grid or SciPy.
Ideal for: 3D pollution / concentration clouds, temperature or humidity fields across a monitoring volume, groundwater head distributions, any scalar field where the interior structure β not just the boundary β matters.
Returns: {filepath, title, rows}
Inputs: data (required), x_column (required), y_column (required), z_column (required), +10 more. Returns: object
create_waffle_chartA
Waffle chart (icon grid) for proportional data. 'X out of 100' visualization.
More intuitive than pie charts for showing proportions.
Ideal for: '1 in 4 Serbs live in Belgrade', budget share, sector breakdown.
Returns: {filepath, title, categories}
Inputs: data (required), names_column (required), values_column (required), theme, +3 more. Returns: object
data_profileA
Understand data structure BEFORE creating charts or transforming.
Returns column names, types, unique counts, null counts, sample values. For numeric columns: min, max, mean, median.
ALWAYS use after get_resource_data() and before create_chart() to choose correct columns.
Inputs: data (required), sample_size. Returns: object
enhance_chart_tooltipsA
Add rich contextual tooltips to any Plotly figure.
Enriches hover with formatted values, deviation from mean, and rank. Without: 'Value: 7150000'. With: 'Value: 7.15M / ProseΔno: 4.2M / Rank: #1'.
Returns: Enhanced figure dict
Inputs: figure (required), unit, show_mean, show_rank, +1 more. Returns: object
export_chart_pdfA
Export a chart to PDF. Requires kaleido (pip install kaleido).
Returns: {filepath, format, width, height} or {error} if kaleido missing
Inputs: figure (required), width, height, filename. Returns: object
export_dataB
Save data from get_resource_data() or transform_data() to file.
Formats: 'csv' (universal), 'json' (API-friendly), 'xlsx' (requires openpyxl).
Inputs: data (required), format, filename. Returns: object
export_to_datawrapperA
Export data to Datawrapper for professional cloud-hosted charts.
Creates a chart on Datawrapper (datawrapper.de) with your data, publishes it, and returns embed URLs and embed code. Requires the DATAWRAPPER_ACCESS_TOKEN environment variable.
Get a free API token at: https://app.datawrapper.de/account/api-tokens
Supported chart types:
'd3-bars-vertical' β vertical bar chart
'd3-bars-horizontal' β horizontal bar chart
'd3-lines' β line chart
'd3-area' β area chart
'd3-pies' β pie chart
'd3-pie-donut' β donut chart
'd3-scatter' β scatter plot
'd3-table' β data table
Inputs: data (required), title (required), labels, chart_type. Returns: object
export_visualizationA
Save a chart from create_chart() to a file.
Inputs: figure (required), format, filename. Returns: object
extract_data_insightsA
Extract surprising findings from data: extremes, trends, outliers, inequality.
Each insight has severity (critical/high/medium/low), headline, and narrative. Sorted by severity. Use AFTER data_profile() to identify time/entity columns.
Returns: {insights: [...], total_found, headline, severity_summary}
Inputs: data (required), time_column, max_insights, entity_column. Returns: object
filter_data_toolA
Filter rows by criteria. Shorthand for transform_data(operation='filter').
Inputs: data (required), filters (required). Returns: object
forecast_dataB
Forecast future values using regression. 'At this rate, X by 2030.'
Returns: {forecast_data, growth_rate, projection_note, r_squared, historical_data, trend_line}
Inputs: data (required), time_column (required), value_column (required), method, +1 more. Returns: object
generate_data_narrativeC
Generate a data story: headline, big number, narrative text.
Returns: {title, headline, big_number, big_label, insights, summary}
Inputs: data (required), title, time_column, max_insights, +1 more. Returns: object
generate_embedA
Generate iframe embed code for sharing a chart in websites/blogs.
Self-contained embed snippet pasteable into any website or CMS. Renders via Plotly.js CDN.
Returns: {iframe_code, width, height, note}
Inputs: figure (required), title, width, height. Returns: object
get_catalog_statsA
Get statistics about the cached dataset catalog.
Summarizes the local catalog (used by intelligent_search/preview_dataset) without triggering a refresh: total datasets, distinct organizations and formats, downloadable count, and cache age.
Returns: {total_datasets, total_organizations, total_formats, downloadable_datasets, formats, organizations, cache_path, cache_age_hours, cache_exists}
Inputs: no named parameters. Returns: object
get_config_toolA
Get the current MCP server configuration settings.
Returns the resolved runtime configuration: API endpoint, rate limit, request timeout, and the cache/export directories. Useful for debugging connectivity or understanding where exported files are written.
Inputs: no named parameters. Returns: object
get_datasetC
Get dataset details. detail_level controls response size.
Inputs: dataset_id (required), detail_level. Returns: object
get_dataset_resourcesA
List the data files (resources) available for a specific dataset.
Use this before get_resource_data() to discover:
Resource IDs (required by get_resource_data)
Available formats (json, csv, xlsx, xls, xml)
File descriptions and sizes
Direct download URLs
Equivalent to get_dataset(detail_level="resources"), exposed as its own tool for callers that only need the file listing.
Inputs: dataset_id (required). Returns: object
get_data_summaryA
Quick schema summary of a resource's data without downloading the full file.
Returns column names, dtypes, row count, and sample values for the first few rows. Much faster than get_resource_data() for large XLSX/CSV files where you only need to know the schema.
Inputs: resource_id (required). Returns: object
get_portal_statisticsB
Get dataset and organization counts for the portal overview.
Inputs: no named parameters. Returns: object
get_resource_dataA
Download and parse a data file from data.gov.rs.
Parses JSON, CSV, XLSX, XLS, and XML automatically. Resource IDs come from get_dataset(detail_level="metadata").
Inputs: resource_id (required). Returns: object
group_data_toolA
Group data by one or more columns with optional aggregations.
Shorthand for transform_data(operation='group'). Returns one row per group with the requested aggregation(s) applied.
Aggregation functions: sum, mean, median, min, max, count, std, var.
Inputs: data (required), group_by (required), aggregations. Returns: object
health_checkA
Check server health and API connectivity.
Inputs: no named parameters. Returns: object
intelligent_searchA
Search datasets with semantic understanding and fallback suggestions (RECOMMENDED).
Uses the cached local catalog for fast results without API rate limits. Expands queries with synonyms and SerbianβEnglish translations, and offers related-dataset suggestions when no exact match is found.
Prefer this over search_datasets() unless you need live API results or organization/format filters.
Inputs: query (required), min_score, max_results, suggest_alternatives. Returns: object
list_organizationsA
List publishers on data.gov.rs. Use returned IDs to filter search_datasets().
Key orgs: Π ΠΠ‘ (statistics), ΠΠΈΠ½ΠΈΡΡΠ°ΡΡΡΠ²ΠΎ ΡΠΈΠ½Π°Π½ΡΠΈΡΠ° (budget), ΠΠ°Π²ΠΎΠ΄ Π·Π° ΡΠ°Π²Π½ΠΎ Π·Π΄ΡΠ°Π²ΡΠ΅ (health).
Returns: {organizations: [{id, name, description, url, logo}], count, page, page_size}
Inputs: page, page_size. Returns: object
list_serbia_districtsA
List 25 administrative districts for create_serbia_map(). Returns recognized names.
Inputs: no named parameters. Returns: object
preview_datasetA
Show dataset metadata with a data preview (first N rows) before downloading.
Use this BEFORE get_resource_data() to understand structure cheaply. Reads metadata and sample rows from the first downloadable resource.
Inputs: dataset_id (required), nrows. Returns: object
refresh_catalogA
Refresh the dataset catalog cache from data.gov.rs.
Re-fetches all datasets from the API and rebuilds the local cache used by intelligent_search() and preview_dataset(). The cache also auto-refreshes every 24h on first use; call this when you need fresh data immediately.
Returns: {total_datasets, cache_path, built_at, duration_seconds, timestamp}
Inputs: no named parameters. Returns: object
search_by_tagB
Find all datasets tagged with specific topics regardless of publisher.
Common tags: "statistika", "budΕΎet", "obrazovanje", "zdravlje", "saobraΔaj", "cene", "registar", "ekologija", "stanovniΕ‘tvo".
Returns: Same shape as search_datasets().
Inputs: tags (required), page, page_size. Returns: object
search_datasetsA
Search data.gov.rs datasets. ALWAYS call this first β never guess dataset IDs.
Returns dataset IDs needed for get_dataset(). Serbian and English both work (e.g. 'stanovniΕ‘tvo' or 'population', 'budΕΎet' or 'budget').
Returns: {datasets: [{id, title, organization, resources, tags, ...}], total, page, page_size, has_next}
Inputs: page, query, format, page_size, +1 more. Returns: object
select_columns_toolA
Select specific columns from data, dropping all others.
Shorthand for transform_data(operation='select').
Inputs: data (required), columns (required). Returns: object
sort_data_toolA
Sort data by one or more columns.
Shorthand for transform_data(operation='sort').
Inputs: by (required), data (required), ascending. Returns: object
suggest_datasetsA
Autocomplete dataset titles. Use when unsure of exact Serbian terms.
Example: suggest_datasets("stanov") β ["StanovniΕ‘tvo Republike Srbije", ...]
Inputs: query (required), size, format. Returns: object
transform_dataC
Transform data: filter, group, aggregate, sort, or select columns.
Inputs: data (required), operation (required), column, columns, +4 more. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 67 tools
With 67 tools, many overlap in purpose (e.g., over 20 chart creation tools, multiple search tools, multiple transform shorthands). Despite detailed descriptions, an agent would struggle to reliably distinguish between similar tools like 'create_chart' and 'create_animated_chart' or 'filter_data_tool' vs 'transform_data(operation="filter")'.
Most tools follow a clean verb_noun pattern with underscores (e.g., search_datasets, create_chart, get_resource_data). A few deviations like 'health_check' and 'get_config_tool' are minor, but the overall naming system is predictable and readable.
67 tools is excessive for a data MCP server. Many highly specialized tools (e.g., 11 distinct 3D chart types) could be consolidated into parameterized versions. The sheer number overwhelms the tool surface and reduces discoverability.
The tool set covers the full lifecycle of working with Serbian open data: discovery (search, browse, suggest), retrieval (get, preview, summary), transformation (filter, sort, group, aggregate), analysis (forecast, benchmark, compare, insight extraction), and extensive visualization (maps, charts, 3D, dashboards, infographics, export). No obvious gaps for its intended domain.
Maintenance
Related MCP Connectors
Search and query 1,500+ OECD statistical datasets via SDMX. Keyless.
Open-data tables (Swiss government data, S&P 500 financials), cleaned and typed; search and SQL.
Discover, resolve, and query official Brazilian economic data with semantic search and provenance.
Search 77k public-sector open data APIs across 10 countries. Read-only, no API key.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables querying and analyzing over 90,000 public datasets from the Spanish Government Open Data Portal (datos.gob.es) using natural language, with tools for search, filtering, metadata access, and SPARQL queries.105MIT
- AlicenseAqualityBmaintenanceEnables AI agents to search and analyze Ukraine's national open-data portal (data.gov.ua) using natural language, with tools for finding datasets, inspecting metadata, and retrieving actual data.6MIT
- AlicenseNot gradedqualityCmaintenanceEnables searching and accessing EU open datasets from data.europa.eu, including metadata discovery and dataset retrieval.91 npmMIT
- AlicenseNot gradedqualityCmaintenanceProvides access to Poland's national open data portal (Otwarte Dane) through natural language queries, enabling users to search and retrieve datasets from dane.gov.pl.88 npmMIT