// SCAN REPORT

Ontario Data

23 tools. 8 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 30 Jun 2026

8 can modify or destroy data

15 read-only

23 tools total

Community server · catalogue entry verified 30/06/2026

How to control Ontario Data ↓

TOOL MAP

What Ontario Data exposes to your agents

Read (15) Write / Execute (7) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Ontario Data tools

Destructive · Medium cache_manage The tool irreversibly removes or clears cached datasets from local storage. Execute · High query_cached The server description mentions 'querying and analyzing datasets' via DuckDB, and the tool name suggests executing queries against cached data. Execute · High query_resource The tool name 'query_resource' and the server's use of DuckDB suggest this executes queries against datasets. Execute · Medium spatial_query The name suggests a query operation, likely executing spatial/geographic queries against datasets via DuckDB.

8 of Ontario Data's 23 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Ontario Data

PolicyLayer is an MCP gateway — it sits between your AI agents and Ontario Data, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "cache_manage": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "download_resource": {
    "limits": [
      {
        "counter": "download_resource_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "cache_info": {
    "limits": [
      {
        "counter": "cache_info_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Ontario Data — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ONTARIO DATA →

Instant setup, no code required.

FULL CATALOGUE

All 23 Ontario Data tools

DESTRUCTIVE 1 tools

Destructive cache_manage Manage the local DuckDB cache: remove or clear cached data.

EXECUTE 4 tools

Execute query_cached query_cached Execute query_resource query_resource Execute spatial_query spatial_query Execute sql_query sql_query

WRITE 3 tools

Write download_resource download_resource Write load_geodata Download and cache a geospatial resource (SHP, KML, GeoJSON) into DuckDB with spatial support. Write refresh_cache Re-download cached resources to get the latest data.

READ 15 tools

Read cache_info Get cache statistics and list all cached datasets. Read check_freshness Check if a dataset is current by comparing its update frequency to its last modification date. Read compare_datasets Compare metadata side-by-side for multiple datasets (can be cross-portal). Read find_related_datasets Find datasets related to a given dataset by shared tags and organization. Read get_dataset_info Get full metadata for a dataset including all resources. Read get_resource_schema Get the column schema and sample values for a datastore resource. Read list_geo_datasets Find all datasets that contain geospatial resources (SHP, KML, GeoJSON). Read list_organizations List government ministries and organizations with dataset counts across all portals. Read list_portals List all available data portals with their platform type and descriptions. Read list_resources List all resources (files) in a dataset with their formats and sizes. Read list_topics List top tags/topics used across data portals, ranked by dataset count. Read preview_data Quick preview of the first N rows of a resource (fetched remotely). Read profile_data Statistical profile and quality check of a cached dataset. Read search_datasets search_datasets Read validate_result validate_result

FAQ

Questions about Ontario Data

Can an AI agent delete data through the Ontario Data MCP server? +

Yes. The Ontario Data server exposes 1 destructive tools including cache_manage. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Ontario Data? +

The Ontario Data server has 3 write tools including download_resource, load_geodata, refresh_cache. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Ontario Data.

How many tools does the Ontario Data MCP server expose? +

23 tools across 2 categories: Read, Write. 15 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Ontario Data? +

Register the Ontario Data MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Ontario Data tool call.

Deterministic rules across all 23 Ontario Data tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ONTARIO DATA →

Instant setup, no code required.

23 Ontario Data tools catalogued and risk-classified — across an index of 43,000+ MCP servers.