Low Risk

get_completion_tool

Get code completion for a prompt

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

AI agents call get_completion_tool to retrieve information from Qiskit Code Assistant 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 get_completion_tool 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-code-assistant-mcp-server.yaml
tools:
  get_completion_tool:
    rules:
      - action: allow

See the full Qiskit Code Assistant MCP Server policy for all 4 tools.

Tool Name get_completion_tool
Category Read
Risk Level Low

Agents calling read-class tools like get_completion_tool 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_completion_tool tool do? +

Get code completion for a prompt. It is categorised as a Read tool in the Qiskit Code Assistant MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_completion_tool? +

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

What risk level is get_completion_tool? +

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

Can I rate-limit get_completion_tool? +

Yes. Add a rate_limit block to the get_completion_tool 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_completion_tool completely? +

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

get_completion_tool is provided by the Qiskit Code Assistant MCP Server MCP server (qiskit-code-assistant-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 Code Assistant 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.