Search for relevant content in an Amazon Q Business application. This operation searches for content within a Q Business application based on the provided query text and returns relevant matches. IMPORTANT: This tool requires valid AWS credentials. If credentials are not provided or are invalid...
High parameter count (10 properties)
Part of the AWS Labs amazon-qindex MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call SearchRelevantContent to retrieve information from AWS Labs amazon-qindex 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 SearchRelevantContent 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:
SearchRelevantContent:
rules:
- action: allowSee the full AWS Labs amazon-qindex MCP Server policy for all 4 tools.
Agents calling read-class tools like SearchRelevantContent 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.
Search for relevant content in an Amazon Q Business application. This operation searches for content within a Q Business application based on the provided query text and returns relevant matches. IMPORTANT: This tool requires valid AWS credentials. If credentials are not provided or are invalid, you must first: 1. Call AuthorizeQBusiness to get an authorization URL 2. Have the user authenticate at that URL to get an authorization code 3. Call CreateTokenWithIAM with the code to get a token 4. Call AssumeRoleWithIdentityContext with the token's identity context to get temporary credentials 5. Finally, call this tool again with those temporary credentials See: https://docs.aws.amazon.com/amazonq/latest/api-reference/API_SearchRelevantContent.html Parameters: application_id (str): The unique identifier of the application to search in query_text (str): The text to search for attribute_filter (Optional[AttributeFilter]): Filter criteria to narrow down search results based on specific document attributes content_source (Optional[ContentSource]): Configuration specifying which content sources to include in the search max_results (Optional[int]): Maximum number of results to return (1-100) next_token (Optional[str]): Token for pagination to get the next set of results qbuiness_region (str): The AWS region in which Qbusiness application is present aws_access_key_id (Optional[str]): AWS access key ID from temporary credentials aws_secret_access_key (Optional[str]): AWS secret access key from temporary credentials aws_session_token (Optional[str]): AWS session token from temporary credentials Returns: Dict: Response syntax: { 'nextToken': 'string', 'relevantContent': [ { 'content': 'string', 'documentAttributes': [ { 'name': 'string', 'value': { # Various value types based on attribute } } ], 'documentId': 'string', 'documentTitle': 'string', 'documentUri': 'string', 'scoreAttributes': { 'scoreConfidence': 'string' } } ] } Raises: ValueError: If there's an error with the Q Business API call or if credentials are missing/invalid. It is categorised as a Read tool in the AWS Labs amazon-qindex 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 SearchRelevantContent. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AWS Labs amazon-qindex MCP Server MCP server.
SearchRelevantContent 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 SearchRelevantContent 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 SearchRelevantContent. 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.
SearchRelevantContent is provided by the AWS Labs amazon-qindex MCP Server MCP server (awslabs.amazon-qindex-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.