List all available Amazon Bedrock Knowledge Bases and their data sources. This tool returns a mapping of knowledge base IDs to their details, including: - name: The human-readable name of the knowledge base - description: The description of the knowledge base - data_sources: A list of data sourc...
Part of the Amazon Bedrock Knowledge Base Retrieval MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call ListKnowledgeBases to retrieve information from Amazon Bedrock Knowledge Base Retrieval 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 ListKnowledgeBases 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:
ListKnowledgeBases:
rules:
- action: allowSee the full Amazon Bedrock Knowledge Base Retrieval MCP Server policy for all 2 tools.
Agents calling read-class tools like ListKnowledgeBases 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.
List all available Amazon Bedrock Knowledge Bases and their data sources. This tool returns a mapping of knowledge base IDs to their details, including: - name: The human-readable name of the knowledge base - description: The description of the knowledge base - data_sources: A list of data sources within the knowledge base, each with: - id: The unique identifier of the data source - name: The human-readable name of the data source ## Example response structure: ```json { "kb-12345": { "name": "Customer Support KB", "description": "Knowledge base containing customer support documentation and FAQs", "data_sources": [ {"id": "ds-abc123", "name": "Technical Documentation"}, {"id": "ds-def456", "name": "FAQs"} ] }, "kb-67890": { "name": "Product Information KB", "description": "Comprehensive product specifications and details", "data_sources": [ {"id": "ds-ghi789", "name": "Product Specifications"} ] } } ``` ## How to use this information: 1. Extract the knowledge base IDs (like "kb-12345") for use with the QueryKnowledgeBases tool 2. Note the data source IDs if you want to filter queries to specific data sources 3. Use the names to determine which knowledge base and data source(s) are most relevant to the user's query. It is categorised as a Read tool in the Amazon Bedrock Knowledge Base Retrieval 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 ListKnowledgeBases. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Amazon Bedrock Knowledge Base Retrieval MCP Server MCP server.
ListKnowledgeBases 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 ListKnowledgeBases 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 ListKnowledgeBases. 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.
ListKnowledgeBases is provided by the Amazon Bedrock Knowledge Base Retrieval MCP Server MCP server (awslabs.bedrock-kb-retrieval-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.