MCP tool to query Amazon Q Business and return a formatted response. This tool provides a Model Context Protocol interface for querying Amazon Q Business. It handles client initialization, query execution, and error handling automatically. Args: query (str): The question or query to send to...
Accepts freeform code/query input (query)
Part of the AWS Labs Amazon Q Business anonymous mode MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call QBusinessQueryTool to retrieve information from AWS Labs Amazon Q Business anonymous mode 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 QBusinessQueryTool 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.
tools:
QBusinessQueryTool:
rules:
- action: allowSee the full AWS Labs Amazon Q Business anonymous mode MCP Server policy for all 1 tools.
Agents calling read-class tools like QBusinessQueryTool have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
MCP tool to query Amazon Q Business and return a formatted response. This tool provides a Model Context Protocol interface for querying Amazon Q Business. It handles client initialization, query execution, and error handling automatically. Args: query (str): The question or query to send to Q Business Returns: str: Formatted response from Q Business or error message if the query fails Examples: >>> qbiz_local_query('What is our company policy on remote work?') "Qbiz response: According to company policy..." >>> qbiz_local_query('') "Error: Query cannot be empty" Note: Requires the following environment variables to be set: - AWS_REGION: AWS region where Q Business is deployed - QBUSINESS_APPLICATION_ID: ID of the Q Business application - AWS credentials must be configured (via AWS CLI, IAM roles, etc.). It is categorised as a Read tool in the AWS Labs Amazon Q Business anonymous mode MCP Server MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for QBusinessQueryTool. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AWS Labs Amazon Q Business anonymous mode MCP Server MCP server.
QBusinessQueryTool is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the QBusinessQueryTool 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.
Set action: deny in the Intercept policy for QBusinessQueryTool. 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.
QBusinessQueryTool is provided by the AWS Labs Amazon Q Business anonymous mode MCP Server MCP server (awslabs.amazon-qbusiness-anonymous-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.