Low Risk

datastore_query

Read actual table rows from a Jersey resource via CKAN datastore_search. Works only for resources with datastore_active=true (get the resource_id from dataset_details). Returns parsed records plus field definitions — e.g. population projections by Year/Age/Sex.

Part of the Jersey Opendata server.

datastore_query is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE JERSEY OPENDATA →

Free to start. No card required.

AI agents call datastore_query to retrieve information from Jersey Opendata without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though datastore_query only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "datastore_query": {}
  }
}

See the full Jersey Opendata policy for all 25 tools.

Get this rule live on your own Jersey Opendata server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY JERSEY OPENDATA →

View all 25 tools →

These attack patterns abuse exactly the kind of access datastore_query gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so datastore_query only ever does what you allow.

SECURE JERSEY OPENDATA →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the datastore_query tool do? +

Read actual table rows from a Jersey resource via CKAN datastore_search. Works only for resources with datastore_active=true (get the resource_id from dataset_details). Returns parsed records plus field definitions — e.g. population projections by Year/Age/Sex.. It is categorised as a Read tool in the Jersey Opendata MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on datastore_query? +

Register the Jersey Opendata MCP server in PolicyLayer and add a rule for datastore_query: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Jersey Opendata. Nothing to install.

What risk level is datastore_query? +

datastore_query is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit datastore_query? +

Yes. Add a rate_limit block to the datastore_query rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block datastore_query completely? +

Set action: deny in the PolicyLayer policy for datastore_query. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides datastore_query? +

datastore_query is provided by the Jersey Opendata MCP server (https://gateway.pipeworx.io/jersey-opendata/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Jersey Opendata tool call.

Deterministic rules across all 25 Jersey Opendata tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.