AI agents call DynamoDB to retrieve information from Aws Claw without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The DynamoDB tool is restricted to read-only operations (listing, describing, and querying). However, it is assigned medium severity rather than low because scan/query operations on DynamoDB tables could potentially expose sensitive data stored in AWS, and an AI agent with credentials access could extract large volumes of data or information about table structures.
From the tool's definition Tool description explicitly lists only read operations: "list tables, describe tables, scan/query items." These are all retrieval and inspection actions with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
list tables, describe tables, scan/query items. It is categorised as a Read tool in the Aws Claw MCP Server, which means it retrieves data without modifying state.
Register the Aws Claw MCP server in PolicyLayer and add a rule for DynamoDB: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Aws Claw. Nothing to install.
DynamoDB 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 DynamoDB rule in your PolicyLayer 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 PolicyLayer policy for DynamoDB. 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.
DynamoDB is provided by the Aws Claw MCP server (necatiarslan/awsclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →