Low Risk

get_refinement_options

List the refinement dimensions (specializations, practice areas, service types, service modes, etc.) available for a business category. Call this BEFORE search_businesses when the user's request is broad (e.g. 'therapist in Greece', 'lawyer in London') so you can politely ask the user whether to ...

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

AI agents call get_refinement_options to retrieve information from Qasperai 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 get_refinement_options 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.

io-github-qasperai-qasper.yaml
tools:
  get_refinement_options:
    rules:
      - action: allow

See the full Qasperai policy for all 8 tools.

Tool Name get_refinement_options
Category Read
MCP Server Qasperai MCP Server
Risk Level Low

Agents calling read-class tools like get_refinement_options 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 get_refinement_options tool do? +

List the refinement dimensions (specializations, practice areas, service types, service modes, etc.) available for a business category. Call this BEFORE search_businesses when the user's request is broad (e.g. 'therapist in Greece', 'lawyer in London') so you can politely ask the user whether to narrow by any of these dimensions — and always offer them the option to see all results without filtering. Returns the attributes defined for the vertical with their possible option values, plus the universal serviceMode options. If refinementAvailable is false, skip refinement and go directly to search_businesses.. It is categorised as a Read tool in the Qasperai MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_refinement_options? +

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

What risk level is get_refinement_options? +

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

Can I rate-limit get_refinement_options? +

Yes. Add a rate_limit block to the get_refinement_options 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 get_refinement_options completely? +

Set action: deny in the Intercept policy for get_refinement_options. 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 get_refinement_options? +

get_refinement_options is provided by the Qasperai MCP server (@qasperai/mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Qasperai

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.