Low Risk

optimization_level

Set transpilation optimisation level

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

qiskit-mcp-server Read Risk 2/5

AI agents call optimization_level to retrieve information from Qiskit MCP Server 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 optimization_level 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.

qiskit-mcp-server.yaml
tools:
  optimization_level:
    rules:
      - action: allow

See the full Qiskit MCP Server policy for all 13 tools.

Tool Name optimization_level
Category Read
Risk Level Low

View all 13 tools →

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

Set transpilation optimisation level. It is categorised as a Read tool in the Qiskit MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on optimization_level? +

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

What risk level is optimization_level? +

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

Can I rate-limit optimization_level? +

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

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

optimization_level is provided by the Qiskit MCP Server MCP server (qiskit-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Qiskit MCP Server

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.