Low Risk

compound_query

The universal commerce query. Combine ANY dimensions: world + emotion + occasion + budget + season + character + profession + age + body type + relationship. Returns worlds with products, /go affiliate links, dimensions, bridges, creators, gaps, and calendar. 'anxious + cottagecore + under-50 + b...

High parameter count (11 properties); Bulk/mass operation — affects multiple targets

Part of the Cultural Intelligence MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

AI agents call compound_query to retrieve information from Cultural Intelligence 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 compound_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.

sincetomorrow-cultural-intelligence.yaml
tools:
  compound_query:
    rules:
      - action: allow

See the full Cultural Intelligence policy for all 26 tools.

Tool Name compound_query
Category Read
Risk Level Low

View all 26 tools →

Agents calling read-class tools like compound_query have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the compound_query tool do? +

The universal commerce query. Combine ANY dimensions: world + emotion + occasion + budget + season + character + profession + age + body type + relationship. Returns worlds with products, /go affiliate links, dimensions, bridges, creators, gaps, and calendar. 'anxious + cottagecore + under-50 + birthday + gift for mom' = one API call with shoppable results across 46 countries and 55 retailers. This is the entire product.. It is categorised as a Read tool in the Cultural Intelligence MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on compound_query? +

Add a rule in your Intercept YAML policy under the tools section for compound_query. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Cultural Intelligence MCP server.

What risk level is compound_query? +

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

Can I rate-limit compound_query? +

Yes. Add a rate_limit block to the compound_query rule in your Intercept 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 compound_query completely? +

Set action: deny in the Intercept policy for compound_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 compound_query? +

compound_query is provided by the Cultural Intelligence MCP server (sincetomorrow/cultural-intelligence). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Cultural Intelligence

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

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

Message sent.

We'll get back to you soon.