MapleStats MCP

npx add-mcp 'https://mcp.maplestats.danielstats.io/mcp'

MapleStats MCP

One MCP server for Canadian open data.

MapleStats MCP gives AI agents (Claude, Cursor and any MCP client) typed access to Canadian open data through one server: Statistics Canada (tables, Census, public use microdata), the Bank of Canada, CMHC, federal agencies, and federal, provincial, territorial and municipal open-data portals, in English and French. Every figure comes back with its citation, its quality flags and its licence, so an answer built on it can be traced to the publisher and checked.

MapleStats MCP donne aux agents IA un accès structuré aux données ouvertes canadiennes par un seul serveur, en français et en anglais. Chaque chiffre revient avec sa citation, ses indicateurs de qualité et sa licence.

Provenance and accountability

• Every figure comes with its citation. A Statistics Canada value carries its table and vector, reference period, release date, unit and scale, geography and a link to the table's page; a Bank of Canada value, its series id and the Valet URL. Every result's provenance block names the source, the exact URL and the time of the query. Results are brief by default (the values, citation, flags, caveats and limits, long row lists as CSV text); detail="full" on call_tool returns the complete provenance block and every field.
• Quality flags are kept. StatCan's "use with caution" and "too unreliable to be published", preliminary and revised stay on each value; public microdata tabulations give a CV and a quality grade per cell where the survey's user guide sets one; staff forecasts are marked as forecasts.
• Gaps are named, not filled. When a figure is not published or a period is not released yet, the server says so and points to the closest published figure. A date range that stops before the newest data gets a note that newer data exist.
• Answers can be checked. check_answer re-reads the StatCan and Bank of Canada figures an answer cites and reports only the problems. reproduce_code writes the R, Python, Stata or Julia script (or Excel Power Query) that pulls the same data straight from the publisher, and reproduce_workbook gives the rows.
• Licences travel with the data. Each result carries the publisher's licence, where it has one, and whether it allows commercial use (provenance.commercial_use; the AESO's market data, for one, are not_allowed).
• StatCan's data and its documentation. Besides tables and vectors, the server reaches definitions, methods and analysis (statcan_reference_*), the survey directory and IMDB metadata (statcan_surveys_*), PUMF codebooks and user guides (statcan_pumf_*), The Daily's articles and release tables (statcan_daily_*) and classifications (rdaas_*).
• Measured. On the 53 questions of the Maple Test, MapleStats answered 91.8% correctly over three runs (November 3, 2026), with no false claims and no invented StatCan table or vector ids. Fifty-three questions are few, part of them were chosen from what MapleStats covers, and later MapleStats runs are in-sample (details).

Why MapleStats

Built by a statistician, for anyone who works with the numbers: economists, demographers, policy analysts, researchers, journalists, students, anyone who needs a Canadian figure they can trust and cite. MapleStats is designed around the mistakes people actually make with official data, and we test it against other tools on public benchmarks: see how it does.

• It knows the traps. Constant vs current dollars, family vs individual income, annual average vs December over December, survey rent vs listing rent: it warns in plain language, and each fitness-for-use caution rests on the publisher's own documentation.
• It says when data do not exist. A series that is not published, a period not released yet or a date with no data gets a plain no, and the nearest figure that does exist.
• The answer can be checked. Before replying, the assistant can send the StatCan and Bank of Canada figures it cites to check_answer, which re-reads them from the source.
• Your work stays reproducible. It writes the R, Python, Stata or Julia script, or the Excel query, that pulls the same data from the source.
• Quality flags and revisions, shown: "use with caution", "too unreliable to be published", preliminary and revised are spelled out on every StatCan value.
• It only reads, in English and French. The server only reads from public sources. The scripts it writes run only if you run them (the full-table ones then save the download under data/raw/), and saving a workbook to disk is opt-in (MAPLE_EXPORT_DIR, on a local server).

Project vision: docs/PROJECT_GUIDE.md. Source coverage: docs/ROADMAP.md. Website: https://maplestats.danielstats.io/.

The easiest way: ask your agent

1. Copy this prompt.
2. Paste it into Claude Code, Codex, Cursor or any agent that can run commands on your computer.
3. Restart the agent when it says so, then ask for data.

Connect the MapleStats MCP server to this agent. Follow the setup steps in https://github.com/dsanchezp18/maplestats-mcp

Instructions for the agent doing the setup

The default is the hosted server: nothing to install, no account, no key.

1. Register this remote (HTTP) MCP server under the name maplestats:

   • Claude Code: claude mcp add --transport http --scope user maplestats https://mcp.maplestats.danielstats.io/mcp
   • Codex CLI: codex mcp add maplestats --url https://mcp.maplestats.danielstats.io/mcp
   • Cursor, Claude Desktop and other mcpServers clients: add the entry below to the client's config file (Cursor: ~/.cursor/mcp.json; Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows), keeping any servers already there.
   • claude.ai and the Claude phone app: on the web, open Settings → Connectors → Add custom connector, name it MapleStats, and enter https://mcp.maplestats.danielstats.io/mcp. Then switch it on from the tools menu in a chat, on the web or in the phone app. Claude asks for approval before each call by default; every tool is read-only, so set them to always allow in the connector's tool permissions.
   • ChatGPT (web): turn on Settings → Security and login → Developer mode, then create a developer-mode app for a remote MCP server with the same address and No Authentication. Every tool is read-only, so ChatGPT should not ask to confirm calls. OpenAI documents this feature for the web.
   • A whole organization: on Claude Team or Enterprise, an Owner adds it once under Organization settings → Connectors → Add custom connector, and each member then connects it. On ChatGPT Business, Enterprise or Edu, an admin turns on Developer mode (Workspace Settings → Permissions & Roles → Connected Data), creates the app, and publishes it (Workspace settings → Apps → Drafts → Publish). The hosted server is shared and limits each client to 60 requests a minute, so a large organization should run its own copy.
   • VS Code: the same entry under a servers key, with "type": "http", in .vscode/mcp.json.

   {
     "mcpServers": {
       "maplestats": {
         "url": "https://mcp.maplestats.danielstats.io/mcp"
       }
     }
   }
   

2. Tell the user to restart or reload the client, then check that the search_tools tool is listed.

3. Only if the client cannot use remote servers, or the user wants everything kept on their own machine, run it locally instead: claude mcp add --scope user maplestats -- uvx maplestats-mcp (needs uv), or the equivalent uvx maplestats-mcp entry for other clients (see Install).

Each client gets 60 requests a minute. Your agent's tool calls (a search phrase, a table number) reach the server and its host, Microsoft Azure (Canada Central). The code keeps no log of them, but its in-memory cache can hold a search phrase or filter in a key or a response until the entry expires or the server restarts. Check Microsoft's terms and privacy statement; for full privacy, run it locally. What it logs: FAQ. Other clients: the Connect page.

Teach your agent to use it well

skills/maplestats/SKILL.md is a portable instruction file (Agent Skills format) for Claude Code, Codex, Cursor and similar agents: start with plan_query, ask for the latest periods, read the caveats, cite table, vector and release date, and run check_answer before answering. Copy it into your agent's skills folder or project instructions. It works with the hosted server and with a local one.

Clients for R, Python and Julia

To call the hosted server from a script, with no agent in between, use the small clients in clients/r, clients/python and clients/julia. Each returns a data frame with its citation. They are not on CRAN, PyPI or the Julia registry yet; each README gives the command to install from GitHub. docs/clients.md explains the design.

Install locally (optional)

Prefer to run it on your machine? It works over stdio with no account or key.

uvx maplestats-mcp                 # run without installing
uv tool install maplestats-mcp     # or install the command once (pip works too)
uv tool upgrade maplestats-mcp     # update

For the development version: uv tool install git+https://github.com/dsanchezp18/maplestats-mcp.git. If you installed the command, use "command": "maplestats-mcp" with no args in the JSON above. On Windows, make sure the directory where uv installs tools is on PATH, and restart the client afterwards.

Using it

Tools are found through search rather than listed flat: call search_tools with a plain-language query (English or French), then call_tool with the name it returns.

{"name": "search_tools", "arguments": {"query": "consumer price index"}}
{"name": "call_tool", "arguments": {"name": "wds_search_cubes", "arguments": {"query": "consumer price index"}}}

plan_query turns a question into an ordered, multi-source plan, and reproduce_code writes the R, Python, Stata or Julia script (or an Excel Power Query) that fetches the same data straight from the source; reproduce_workbook returns the rows as a formatted Excel workbook. Before replying with figures, the assistant can call check_answer with the StatCan and Bank of Canada figures it cites: it re-reads them from the source and returns only the problems (a different value, a missed scale factor, a newer period, another geography, an unadjusted series), each with a fix. The calc_ tools do the arithmetic across series that assistants get wrong, from StatCan and Bank of Canada series, and return the formula and every input's citation with the result: calc_ratio (one series over another, aligned by period, scale factors applied), calc_rank (places ranked for one period, ties shared), calc_cagr (compound annual growth between two periods) and calc_count_changes (how many times a series moved, such as policy rate decisions). Mismatched frequencies or units are refused, not guessed. Every tool accepts lang: "en"|"fr"; some sources only publish English content (for example Yukon's CKAN portal, the World Bank's indicator definitions and the PMPRB), so there lang changes the labels MapleStats adds, not the source's own text. Every response has a provenance block: source, URL, query time, freshness and limits. Through call_tool results are brief by default: values, periods, unit and scale, the citation, status flags, caveats, limits, licence and URL, with a list of six or more rows sent as one CSV text block ({"format": "csv", "csv": ...}) and the boilerplate (query time, cache flag, schema name, freshness, the reproduce hint) left out. Pass detail="full" for every field and the whole provenance block, rows as JSON objects. reproduce_code and reproduce_workbook always read the full result. docs://catalogue describes every module in both languages. The guided prompts take lang too, and each docs://<module>/... resource has a French twin at docs://<module>/fr/... (for example docs://statcan/fr/pieges).

To call the sources from Python without MCP, see docs/library.md.

What to watch for

MapleStats retrieves data directly from the original sources and returns values as published. When a result is trimmed, scaled, cleaned or computed, it says so in its provenance block or its notes; series values come unscaled, with the scale factor beside them. When a source is down or blocks the request, the tool returns an error, not a silent gap or a substitute value.

The risk is in the use. An AI assistant can pick the wrong table, geography or reference period, and the answers, summaries and analysis it writes are AI-generated and can contain errors. For anything you would publish, spot-check a few figures against the source's own site and use reproduce_code to fetch them again outside the assistant. Publishers revise their figures, so a value retrieved today can differ from an earlier one.

Each dataset keeps its own licence and attribution terms, shown in the result's provenance; credit the publisher, not MapleStats. MapleStats is an independent project, not affiliated with or endorsed by Statistics Canada, the Bank of Canada, CMHC or any other data provider. It is provided as is, depends on upstream services that can change or go offline, and is not professional, legal or financial advice. Parts of the code and tests were written with AI assistance; the discovery benchmark's questions were written by one AI session and reviewed by a second, independent one, not yet by a person (tests/discovery_benchmark/REVIEW.md).

What it covers

459 tools in 90 modules. Read docs://catalogue (or docs_read_resource through call_tool) for the full, bilingual list.

Area	Tool prefixes	Covers
Statistics Canada	wds_, sdmx_, sdmx_space_, rdaas_, cimt_, statcan_*	Tables and series, the extra SDMX spaces (energy information, shared data), classifications, Census Profiles 2001–2021, public use microdata (codebooks, weighted tables, standard errors where the survey's guide gives a method, the LFS included; SAS, SPSS and Stata files read), merchandise trade by commodity (CIMT), open databases (LODE), The Daily and the tables inside each release as first published, delta files, indicators, surveys, census geography
Bank of Canada	boc_	Valet series, groups, observations
CMHC	cmhc_, cmhc_dt_	Housing Market Information Portal and Excel data tables
Federal agencies	eccc_, eccc_coverages_, eccc_datamart_, ised_*, gazette_, tc_recalls_, recalls_, cdc_, cfia_, fcac_, finance_, cihi_, phac_infobase_, hc_*, pmra_, pmprb_, gc_infobase_, disclosure_, cer_, nrcan_*, dfo_iwls_, dfo_landings_, cgc_, nfd_, ircc_*, cbsa_, cbsa_tariff_, pbo_, competition_bureau_, elections_results_, elections_financial_returns_, cra_digital_economy_registry_, cra_charities_, jobbank_, telecom_, earthquakes_, borealis_, isc_	Weather, climate and gridded climate projections, pollutant releases and emissions (NPRI, GHGRP, NAPS), corporations and IP, regulations, recalls, dairy, animal disease, consumer banking, federal and provincial fiscal tables, health, drugs, natural health products, medical devices, adverse reactions, pesticides, spending, federal contracts, grants and travel and hospitality disclosures, energy, energy use by sector (NRCan, to 2023), mineral production, oceans, commercial fisheries landings, grain, forestry, immigration and application processing times, Job Bank wages and outlooks by occupation, registered charities, mobile and Internet plan prices, border wait times, customs tariff rates, budgets, mergers, elections, earthquakes, university-library data tables, First Nation profiles, registered population and drinking water advisories
Wildland fire	cwfis_, nrcan_nbac_, ab_wildfire_	NRCan's Canadian Wildland Fire Information System (satellite hotspots, fire danger, weather stations), burned areas, and Alberta Wildfire's live fire status
Electricity	electricity_ontario_, electricity_quebec_, electricity_alberta_, oeb_	IESO (Ontario) demand, generation and prices; Hydro-Québec demand, generation and trade (CC BY-NC 4.0: credit Hydro-Québec, non-commercial use only); AESO (Alberta) hourly, daily and monthly pool prices, load and current generation by fuel (AESO terms: non-commercial use only); Ontario Energy Board datasets
Parliament and elected officials	ourcommons_, senate_, represent_	MPs and their roles, party standings, Cabinet, Senate votes; elected officials and districts for a postal code via Open North's Represent (unofficial)
Provincial agencies	aer_, bcgw_, bc_stats_, bc_env_, bc_lobbyists_, drivebc_, ab_economic_, ab_opendata_, isq_, nl_stats_, yukon_stats_, nwt_stats_, elections_provincial_, on_fir_	Alberta Energy Regulator (well licences, production, ST98 energy outlook), BC Geographic Warehouse, BC Stats Excel tables, BC environmental monitoring (air quality, snow, groundwater, streamflow), BC lobbyists registry, DriveBC road events, Alberta Economic Dashboard, Open Alberta files, Institut de la statistique du Québec, the Newfoundland and Labrador, Yukon and Northwest Territories statistics bureaus, provincial general election results (Quebec, Alberta, British Columbia, Saskatchewan, Manitoba), Ontario's municipal Financial Information Return (every schedule of every municipality, 2000 on)
Housing (links only)	crea_	Links, release timing and terms for CREA's MLS® Home Price Index; no values, because CREA's terms allow private, non-commercial analysis only
International	worldbank_, bis_, oecd_, eurostat_, ilo_, abs_, ons_, fed_, ecb_	World Bank World Development Indicators for Canada and peer countries (CC BY 4.0); Bank for International Settlements statistics: policy rates, debt service ratios, credit, house prices, banking and payment statistics (free reuse with citation); OECD Data Explorer for Canada and its peers: Economic Outlook projections, productivity, unit labour costs, PPPs, tax revenue, house prices, leading indicators (any use with credit, third-party data excepted); Eurostat for the EU, the euro area and member states (CC BY 4.0, not commercially for non-EU countries' data); ILOSTAT, the International Labour Organization's internationally comparable labour statistics for Canada and its peers: unemployment, participation, hours, earnings, minimum wages and ILO modelled estimates (CC BY 4.0); the Australian Bureau of Statistics' headline inflation, labour force, GDP, wage and population series, each with the Canadian table to pair with, and any ABS dataset by SDMX key (CC BY 4.0); the UK Office for National Statistics' headline inflation, GDP and labour market series, each with the Canadian table to pair with (Open Government Licence v3.0); US Federal Reserve Board releases: the federal funds rate, Treasury yields, the Canadian dollar per US dollar, industrial production and capacity utilization, money and credit (public domain, Board cited); European Central Bank Data Portal: key interest rates, €STR, euro reference rates (EUR/CAD), euro area HICP, money and credit (free reuse with 'Source: ECB statistics', third-party data excepted)
Open-data portals	ckan_, arcgis_hub_, socrata_ + portal	Federal, provincial, territorial and municipal catalogues (*_list_portals names each one)
Other municipal	opendatasoft_vancouver_, nl_opendata_, eps_, ets_, epcor_, bc_transit_, toronto_	Vancouver, Newfoundland and Labrador, Edmonton police, transit and water quality, BC Transit real-time vehicle positions, arrival predictions and service alerts, City of Toronto neighbourhood profiles, RentSafeTO building scores, short-term rental registrations and DineSafe inspections
Transit schedules	transit_ + agency	Static GTFS timetables of the STM (buses), OC Transpo, Calgary Transit, VIA Rail, GO Transit, UP Express, the BC Transit systems and the Quebec networks listed on Données Québec (exo, RTC, STL, STS and others), plus further agencies from Statistics Canada's 2025 Canadian Public Transit Network Database: stops, routes, scheduled departures, frequency by hour

Other federal series (CRA, OSFI, ISED insolvency) are ordinary open.canada.ca datasets, reachable with ckan_search_datasets(portal="federal", fq="organization:<org>").

Not covered: CAPP's Statistics Handbook, Petrinex and Payments Canada were not built, because their terms or download hosts do not permit automated access. CanadaBuys, OpenParliament.ca and the Toronto Transit Commission's own schedule download were removed for the same reason (the TTC schedule is still served from Statistics Canada's national transit database). The City of Whitehorse's open data files are not built: its terms bar commercial reproduction without the City's written consent. The City of Toronto's files (as opposed to its DataStore tables) are not read: its portal's robots.txt disallows automated file downloads. The City of Hamilton's portal is left out because it answers automated requests with a Cloudflare challenge (Niagara Open Data did too until 2026-11-08, and is now covered). The 2006-2016 census data tables and the 2016 Census Profile service were removed because Statistics Canada's www12 host answers automated clients with a bot challenge, 503 errors or timeouts (the 2021 profile and the WDS tables remain). Justice Laws (federal statutes and regulations) is out of scope, because legislation text is not data this server carries, and the Saskatchewan Bureau of Statistics' Provincial Economic Accounts were not built: they are under Crown copyright, for non-commercial reuse only, and the site's terms bar automated access. The roadmap records each decision.

Development

uv sync                          # install
uv run ruff check src tests scripts  # lint
uv run ruff format src tests scripts  # format
uv run pyright                   # type check
uv run pytest                    # unit tests (mocked, no network)

.\scripts\verify.ps1 runs that gate plus every scripts/smoke_test*.py against the live APIs. The website is generated from the tool registry: uv run python scripts/build_site.py writes build/site/. See AGENTS.md for the contributor guide and how to add a source module.

Hosting

MAPLE_TRANSPORT=http MAPLE_HOST=0.0.0.0 MAPLE_PORT=8000 uv run maplestats-mcp serves HTTP instead of stdio. Docker Compose does the same in Docker, but the image and docker-compose.yml set MAPLE_REQUIRE_AUTH=1, so the server refuses to start until MAPLE_AUTH_TOKEN is set: MAPLE_AUTH_TOKEN=<a long random string> docker compose up --build. Clients then send that token as a bearer token. Docker is optional and unnecessary on a personal computer. If the server is exposed beyond your machine, set MAPLE_AUTH_TOKEN and keep MAPLE_REQUIRE_AUTH=1. GET /health reports uptime and version. GET /stats is public, needs no token and reports calls per tool name and day, each tool's p50 and p95 duration, and each upstream host's error counts and circuit-breaker state (see MAPLE_USAGE_STATS and MAPLE_BREAKER below). After repeated failures (timeouts, connection errors, 5xx answers, Cloudflare challenges) a host is paused for a cooldown: its tools fail at once with an "unavailable" error that says when to retry, instead of waiting for another timeout. The docs://status resource lists the paused hosts.

Env var	Default	Purpose
MAPLE_TRANSPORT	stdio	stdio for local clients, http for hosting
MAPLE_HOST / MAPLE_PORT	127.0.0.1 / 8000	HTTP bind address
MAPLE_AUTH_TOKEN, MAPLE_REQUIRE_AUTH	unset, 0	Bearer token required on /mcp; refuse to start without one if 1. The Docker image and docker-compose.yml default MAPLE_REQUIRE_AUTH to 1
MAPLE_RATE_LIMIT_REQUESTS / MAPLE_RATE_LIMIT_WINDOW_SECONDS	120 / 60	Per-client rate limit
MAPLE_MAX_CONCURRENT_REQUESTS	8	In-flight request cap; the excess waits 5 s, then gets 503
MAPLE_MAX_REQUESTS_PER_CLIENT	0 (off)	In-flight requests one client (IPv6: one /64) may hold; past it, 429. Leave off where many people share an address
MAPLE_SSL_CERTFILE / MAPLE_SSL_KEYFILE	unset	TLS in-process
MAPLE_TRUST_PROXY_HEADERS	0	Rate-limit on X-Forwarded-For; only behind a proxy that sets it
MAPLE_TRUSTED_PROXY_HOPS	1	Proxies that append to X-Forwarded-For; the client address is read that many entries from the right
MAPLE_ALLOWED_ORIGINS	project website, localhost	Browser origins allowed on /mcp (comma-separated, *. and :* wildcards); others get 403, clients without an Origin are allowed
MAPLE_CACHE_MAX_ENTRIES	2000	Response cache size per TTL bucket
MAPLE_CACHE_MAX_MB	128	Estimated memory cap for the response cache, all buckets together
MAPLE_PARSE_WORKERS / MAPLE_PARSE_TIMEOUT_SECONDS	4 / 60	Threads for parsing Excel and CSV files, and the time one parse may take
MAPLE_TOOL_TIMEOUT_SECONDS	120	Longest a tool call may run
MAPLE_BREAKER	1	Pause requests to an upstream host after repeated failures; 0 sends every request
MAPLE_BREAKER_FAILURES / MAPLE_BREAKER_WINDOW_SECONDS / MAPLE_BREAKER_COOLDOWN_SECONDS	5 / 300 / 60	Failures in a row, within the window, that pause a host, and how long before one probe request is sent
MAPLE_PUMF_TABULATE	1	0 hides statcan_pumf_tabulate (it downloads whole PUMF ZIPs); search, listings and codebooks stay
MAPLE_QUERY_SERIES	1 locally, 0 over HTTP	0 hides wds_query_series (server-side SQL): off by default when serving HTTP, since one query could use more memory than a small instance has
MAPLE_PRELOAD	0 locally, 1 over HTTP	1 imports every module and builds the search index at startup, before the port opens, so the first calls after a start are not slow; off locally so desktop clients start fast
MAPLE_PUMF_CACHE_DIR, MAPLE_PUMF_CACHE_MAX_GB	system temp, 5	Downloaded microdata cache; use a persistent volume when hosted
MAPLE_CLIENT_IP_HEADER	unset	Header the outermost proxy sets to the caller's own address (Cloudflare's CF-Connecting-IP), used for the per-client rate limit when MAPLE_TRUST_PROXY_HEADERS is on; set it only when every request passes through that proxy
MAPLE_DUCKDB_MEMORY_LIMIT	unset	Memory limit for DuckDB queries over downloaded files (patents, open databases, microdata), such as 256MB; beyond it DuckDB spills to the temporary folder. Set it on a small hosted instance
MAPLE_DUCKDB_TEMP_DIR, MAPLE_DUCKDB_TEMP_MAX_GB	system temp (maplestats-duckdb), 1	Where DuckDB spills past its memory limit (each query in its own subfolder, removed when it ends), and the most one query may spill
MAPLE_QUERY_MEMORY_MB, MAPLE_QUERY_MAX_CONCURRENT	256, 2	wds_query_series runs each SQL query in its own process: the memory it may use beyond its start (enforced on Linux), and how many run at once
MAPLE_LODE_CACHE_DIR, MAPLE_LODE_CACHE_MAX_GB	system temp, 3	Where StatCan open-database (LODE) archives are unpacked, and the size cap (least recently used files go first); use a persistent volume when hosted
MAPLE_LODE_MAX_DOWNLOAD_MB	300	Largest open-database archive one call may download; 0 turns downloads off
MAPLE_IP_HORIZONS_CACHE_DIR, MAPLE_IP_HORIZONS_CACHE_MAX_GB	system temp, 3	CIPO patent table cache
MAPLE_CBSA_TARIFF_CACHE_DIR	system temp	Customs Tariff editions as Parquet (under 1 MB each, newest 12 kept)
MAPLE_ON_FIR_CACHE_DIR, MAPLE_ON_FIR_CACHE_MAX_MB	system temp, 500	Ontario FIR years kept as Parquet (about 3 MB each); use a persistent volume when hosted
MAPLE_EXPORT_DIR	unset (no files saved)	Folder where reproduce_workbook saves Excel workbooks on a local server. Unset, the workbook comes back as base64 and every tool is read-only
MAPLE_SEARCH, MAPLE_SEMANTIC_DIR	bm25, unset	hybrid fuses BM25 with a local multilingual-e5-small index (needs the [semantic] extra and python -m maplestats_mcp.shared.semantic build); off by default, see tests/discovery_benchmark/phase2.md
MAPLE_RESPONSE_MAX_BYTES	200000	Byte budget for one tool result (minimum 10,000); a larger result has its biggest lists trimmed, and provenance.limits says what was kept and how to get the rest
MAPLE_GOATCOUNTER_URL, MAPLE_GOATCOUNTER_TOKEN	unset	With both set (an https GoatCounter site and an API token allowed to record pageviews), each counted tool call is also sent there as the event mcp/<instance>/<tool> (/error appended on failure), in batches each minute, so counts outlive restarts and several hosts add up; no arguments or addresses, no_sessions on
MAPLE_INSTANCE_NAME	server	The <instance> label in those events (azure, render)
MAPLE_OPENAI_APPS_CHALLENGE	unset	Token served as plain text at GET /.well-known/openai-apps-challenge (no auth), which OpenAI's plugin portal fetches to verify the domain; unset, that path answers 404
MAPLE_USAGE_STATS	1	Counts calls and durations per tool name and UTC day, each failure's error code (not_found, invalid_input, ...: a fixed list, never the message), and upstream errors per host (never arguments or client addresses), in memory, and serves them at the public /stats route; 0 turns both off
MAPLE_USAGE_STATS_FILE	unset	A JSON file the /stats call counts and error codes (per tool and per UTC day, kept 400 days) are read from at startup and saved to every minute and on exit, so a restart or deploy does not reset them; point it at a persistent volume. Several processes saving to one file add up rather than overwrite each other. Latencies stay in memory
MAPLE_DELTA_MAX_SCAN_MB / MAPLE_DELTA_MAX_SCAN_SECONDS	400 / 75	How much of a Delta File one statcan_delta_read_table call streams (seconds kept 30 under the tool timeout)
MAPLE_DELTA_INDEX_DIR	system temp	Saved Delta File resume points (a few MB per day); off keeps them in memory only

License

MIT. Third-party notices are in THIRD_PARTY_NOTICES.md.

Security and conduct

Report a vulnerability privately through GitHub's private vulnerability reporting; see SECURITY.md. Changes are recorded in CHANGELOG.md, and community expectations in CODE_OF_CONDUCT.md.

Acknowledgments

MapleStats owes its architecture to EcuDataMCP, the MCP server for Ecuador's open data that I help maintain with DweskZ and its other contributors. Its approach to Canadian data owes much to the R developers who got there first: Jens von Bergmann (mountainMath) and his co-authors, including Dmitry Shkolnik (dshkol), Thierry Warin (statcanR), Valentin Lucet (rgovcan), and others. Thanks to them, and to everyone who publishes Canadian data in the open.

For other ways to get Canadian data, see the alternatives.