Statistics Canada MCP Server
Related Servers
Alternatives to Statistics Canada MCP Server
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceMCP server providing access to Statistics Canada time-series data via web data.408 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables an MCP client to discover ABS datasets, inspect SDMX dimension order and codelists, and run bounded statistical-data queries against the Australian Bureau of Statistics Data API.MIT
- AlicenseNot gradedqualityFmaintenanceProvides access to Statistics Canada official statistics without authentication, enabling AI agents to query Canadian economic and demographic data.1 npmMIT
- AlicenseAqualityBmaintenanceGives AI agents structured, typed access to Canadian open data through a single server covering Statistics Canada tables, Census and public use microdata, the Bank of Canada, CMHC, federal agencies and federal, provincial, territorial and municipal open-data portals, in English and French. It offers roughly 200 tools for querying, planning multi-source queries, and generating reproduction code in R, Python, Stata or Julia.3262 PyPI1MIT

cat.idescat/mcpofficial
AlicenseNot gradedqualityBmaintenanceEnables any MCP client to discover and query official Catalonia statistics through read-only tools and resources, including statistic catalogues, table metadata, filtered JSON-stat data, territorial breakdowns, and Markdown tables with source attribution.MIT- AlicenseAqualityCmaintenanceMCP server giving LLMs live access to Statistics Canada's full catalogue of 8,200+ data tables via the Web Data Service, with tools to search tables, inspect dimensions, and fetch time series data using plain-language prompts.540 npmMIT
TDQS
Scored across 25 tools
Multiple tools overlap in purpose, e.g., get_all_cubes_list vs get_all_cubes_list_lite, get_sdmx_data vs get_sdmx_rows, get_series_info vs get_series_info_from_vector, and two changed-series-data tools that differ only by identifier type. The detailed descriptions help, but the boundaries between these tools are subtle enough that an agent could easily pick the wrong one.
Most tools follow a snake_case verb_noun pattern (get_, list_, create_, insert_, etc.), but the SDMX family is inconsistent: get_sdmx_data, get_sdmx_rows, get_sdmx_vector_data, and get_sdmx_structure all sound like data retrieval tools, and get_series_info vs get_series_info_from_vector is confusingly similar. Naming is readable but not perfectly predictable.
At 25 tools, the server sits at the high end of 'feels heavy'. The scope is broad (Statistics Canada API plus SQLite persistence), which justifies many tools, but some functions could be merged (e.g., get_sdmx_data and get_sdmx_rows) to reduce redundancy and cognitive load.
The tool surface covers the full data lifecycle: cube discovery, search, metadata, series info, SDMX data, vector access, changed-data tracking, code-set definitions, plus a full SQLite persistence layer for storing and querying results. Minor gaps exist (e.g., no direct batch-metadata fetch, and lastNObservations can't combine with date ranges), but no critical dead ends.