Low Risk

oracle_query

Execute a read-only SELECT/WITH query on Oracle. Rejects non-SELECT statements and enforces a row limit by appending FETCH FIRST when needed. Use max_rows to cap returned rows; when url includes maxRows, it overrides max_rows. Optional url supports per-call connection in the form oracle://user:pa...

Part of the Oracle Link server.

oracle_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 ORACLE LINK →

Free to start. No card required.

AI agents call oracle_query to retrieve information from Oracle Link 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 oracle_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": {
    "oracle_query": {}
  }
}

See the full Oracle Link policy for all 3 tools.

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

ENFORCE ON MY ORACLE LINK →

These attack patterns abuse exactly the kind of access oracle_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 oracle_query only ever does what you allow.

SECURE ORACLE LINK →

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

What does the oracle_query tool do? +

Execute a read-only SELECT/WITH query on Oracle. Rejects non-SELECT statements and enforces a row limit by appending FETCH FIRST when needed. Use max_rows to cap returned rows; when url includes maxRows, it overrides max_rows. Optional url supports per-call connection in the form oracle://user:password@host:port/service?privilege=SYSDBA&maxRows=N. Returns rows as an array of objects keyed by column names. Intended strictly for data retrieval.. It is categorised as a Read tool in the Oracle Link MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on oracle_query? +

Register the Oracle Link MCP server in PolicyLayer and add a rule for oracle_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 Oracle Link. Nothing to install.

What risk level is oracle_query? +

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

Can I rate-limit oracle_query? +

Yes. Add a rate_limit block to the oracle_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 oracle_query completely? +

Set action: deny in the PolicyLayer policy for oracle_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 oracle_query? +

oracle_query is provided by the Oracle Link MCP server (@studious-xiaoyu/oracle-link). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Oracle Link tool call.

Deterministic rules across all 3 Oracle Link 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.