Datos Gob Do Mcp Server
Exposes the Dominican Republic's official open data portal (datos.gob.do, a CKAN 2.11 instance) as seventeen typed tools for Claude. Search across 1,000+ datasets from 266 government institutions, fetch metadata and resources, download CSVs and Excel files with preview support, and run typed analytics (filters, aggregations, raw SQL) over a local DuckDB cache that persists downloaded datasets as Parquet. Built for journalists querying budget execution, researchers analyzing public health data, or anyone who wants to ask "how much does the Judicial Branch spend on salaries" without manually navigating a data portal. Created by alcastaro, inspired by France's datagouv-mcp but adapted for CKAN infrastructure.
- GitHub stars
- 3
- tools
- 27
- transport
- STDIO
- last updated
- Aug 13, 2026
Tools
27 toolsPublic tool metadata for what this MCP can expose to an agent.
search_datasetsSearch datasets by keyword, organization, tag, or group. Combinable filters, pagination.
Search datasets by keyword, organization, tag, or group. Combinable filters, pagination.
No parameter schema in public metadata yet.
get_datasetFull metadata for a dataset: title, description, licence, author, and every resource with its direct download URL.
Full metadata for a dataset: title, description, licence, author, and every resource with its direct download URL.
No parameter schema in public metadata yet.
list_recent_datasetsDatasets sorted by most-recent modification. Useful for monitoring portal updates.
Datasets sorted by most-recent modification. Useful for monitoring portal updates.
No parameter schema in public metadata yet.
get_site_statsPortal-wide counts (datasets, organizations, groups, tags).
Portal-wide counts (datasets, organizations, groups, tags).
No parameter schema in public metadata yet.
get_resourceMetadata for a single resource (URL, format, size, date).
Metadata for a single resource (URL, format, size, date).
No parameter schema in public metadata yet.
search_resourcesSearch resources by name.
Search resources by name.
No parameter schema in public metadata yet.
download_resource_previewDownload a file and return N rows. CSV, TSV, XLSX, XLS, ODS, JSON. 5 MB cap. Sample mode: head / tail / random.
Download a file and return N rows. CSV, TSV, XLSX, XLS, ODS, JSON. 5 MB cap. Sample mode: head / tail / random.
No parameter schema in public metadata yet.
check_resourcesAsk up to 25 URLs whether their files can actually be downloaded, without downloading them. Returns a class per URL — reachable, browser challenge, site rule, dead link, no answer — because a catalog entry is not evidence the file is still there.
Ask up to 25 URLs whether their files can actually be downloaded, without downloading them. Returns a class per URL — reachable, browser challenge, site rule, dead link, no answer — because a catalog entry is not evidence the file is still there.
No parameter schema in public metadata yet.
get_resource_schemaColumn names, inferred types, sample values. The cheap reconnaissance step before any aggregation.
Column names, inferred types, sample values. The cheap reconnaissance step before any aggregation.
No parameter schema in public metadata yet.
summarize_resourceAuto profile: row count, per-column nulls and distinct counts, min/max/mean on numerics, top-N on categoricals.
Auto profile: row count, per-column nulls and distinct counts, min/max/mean on numerics, top-N on categoricals.
No parameter schema in public metadata yet.
filter_resourceTyped WHERE / SELECT / ORDER BY / LIMIT. Ops: =, !=, <, <=, >, >=, in, not_in, contains, starts_with, ends_with, is_null, is_not_null.
Typed WHERE / SELECT / ORDER BY / LIMIT. Ops: =, !=, <, <=, >, >=, in, not_in, contains, starts_with, ends_with, is_null, is_not_null.
No parameter schema in public metadata yet.
aggregate_resourceTyped GROUP BY + aggregations + HAVING + ORDER BY. Fns: count, count_distinct, sum, avg, mean, median, min, max, stddev, variance.
Typed GROUP BY + aggregations + HAVING + ORDER BY. Fns: count, count_distinct, sum, avg, mean, median, min, max, stddev, variance.
No parameter schema in public metadata yet.
quantiles_resourcePercentile distribution (p25/p50/p75/p90/p95/p99) of numeric columns.
Percentile distribution (p25/p50/p75/p90/p95/p99) of numeric columns.
No parameter schema in public metadata yet.
find_duplicates_resourceRows duplicated on given columns (or all). Essential for payroll and census quality checks.
Rows duplicated on given columns (or all). Essential for payroll and census quality checks.
No parameter schema in public metadata yet.
detect_outliers_resourceRows outside the IQR fence on a numeric column, sorted by distance from the median.
Rows outside the IQR fence on a numeric column, sorted by distance from the median.
No parameter schema in public metadata yet.
query_resourcePower-user escape hatch: read-only SQL against table data. SELECT/WITH only; DDL/DML/COPY/PRAGMA/ATTACH/LOAD rejected, and sandboxed.
Power-user escape hatch: read-only SQL against table data. SELECT/WITH only; DDL/DML/COPY/PRAGMA/ATTACH/LOAD rejected, and sandboxed.
No parameter schema in public metadata yet.
save_query_to_csvWrite a filter or SQL result to a local CSV. Absolute destination, or the default ~/Downloads/datosgobdo-exports/. Disabled in hosted mode.
Write a filter or SQL result to a local CSV. Absolute destination, or the default ~/Downloads/datosgobdo-exports/. Disabled in hosted mode.
No parameter schema in public metadata yet.
get_cache_statsOn-disk Parquet cache statistics, plus the server's own identity and effective security mode.
On-disk Parquet cache statistics, plus the server's own identity and effective security mode.
No parameter schema in public metadata yet.
clear_cacheWipe the local Parquet cache. The only non-read-only tool in the server (destructiveHint: true). Disabled in hosted mode.
Wipe the local Parquet cache. The only non-read-only tool in the server (destructiveHint: true). Disabled in hosted mode.
No parameter schema in public metadata yet.
list_organizationsPublishing institutions with a dataset count each.
Publishing institutions with a dataset count each.
No parameter schema in public metadata yet.
get_organizationDetail for one institution (description, dataset count, URL).
Detail for one institution (description, dataset count, URL).
No parameter schema in public metadata yet.
list_groupsThematic categories with counts.
Thematic categories with counts.
No parameter schema in public metadata yet.
list_tagsTags, optionally filtered by prefix.
Tags, optionally filtered by prefix.
No parameter schema in public metadata yet.
autocompleteResolve partial names for datasets, organizations, groups or tags — for when the user only gives part of a name.
Resolve partial names for datasets, organizations, groups or tags — for when the user only gives part of a name.
No parameter schema in public metadata yet.
load_resource_to_bigqueryResource → Parquet cache → GCS upload → BigQuery external table (default, zero-ETL) or load job.
Resource → Parquet cache → GCS upload → BigQuery external table (default, zero-ETL) or load job.
No parameter schema in public metadata yet.
list_bigquery_exportsList tables in a BigQuery dataset.
List tables in a BigQuery dataset.
No parameter schema in public metadata yet.
get_bigquery_table_infoSchema, row count and source URIs of a table.
Schema, row count and source URIs of a table.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
datosgobdo-mcp
Ask an AI assistant a question about Dominican public data, and get an answer traced back to the government file it came from.
This is a Model Context Protocol server for datos.gob.do, the Dominican Republic's official open-data portal. It plugs into Claude Desktop, Claude Code, Cursor, ChatGPT Desktop or any MCP-compatible client, and lets the model search the catalog, download the actual files, parse them, and run real analysis — without you writing code, opening a URL, or downloading a spreadsheet.
Details
- Repository
- github.com/alcastaro/datos.gob.do-mcp-server
- Category
- Data & Analytics
- Package
dominican-open-data-mcp- Transport
- STDIO
- Registry
- MCP registry, active
Related Data & Analytics MCP servers
View all
Xmlriver Mcpartgas1/xmlriver-mcpGoogle/Yandex SERP parsing and Yandex Wordstat keyword frequency via XMLRiver XML API3stars
Numbersmcpaernouddekker/macos-mcpMCP server for macOS Numbers.app — spreadsheet access via AppleScript0stars
ClearMarketjdsource/clearmarketReference data for prediction markets: graded resolution clarity, cross-venue links, provenance.3stars
sigrok MCP Serverkenosinc/sigrok-mcp-serverWraps sigrok-cli for signal analysis: capture data, decode protocols, and query instruments.3stars
FastMCP server for surgical queries against a vault knowledge graph (NetworkX noadelaidasofia/graph-query-mcpFastMCP server for surgical queries against a vault knowledge graph (NetworkX node-link JSON).…2stars
DaedalMap Geographic Data and Toolsxyver/daedal-mapConnect geographic IDs, places, shapes, and published data through DaedalMap tools.2stars