Documentation on integrating tools with AWS AgentCore agents.
AI agents call agentcore_tools to retrieve information from AWS AgentCore MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a documentation/reference tool that provides guidance material. Reading documentation has no side effects and poses minimal risk even if misused by an agent, as it cannot alter systems, execute code, or cause data loss. Confidence is high because the description explicitly states this is documentation rather than an operational capability.
From the tool's definition Tool name 'agentcore_tools' and description 'Documentation on integrating tools with AWS AgentCore agents' indicate this retrieves informational content about framework integration patterns.
Attacks that exploit this kind of access
Documentation on integrating tools with AWS AgentCore agents. It is categorised as a Read tool in the AWS AgentCore MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AWS AgentCore MCP Server MCP server in PolicyLayer and add a rule for agentcore_tools: 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 AgentCore MCP Server. Nothing to install.
agentcore_tools 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 agentcore_tools 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 agentcore_tools. 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.
agentcore_tools is provided by the AWS AgentCore MCP Server MCP server (weiwarren/agentcore-mcp-server). 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 →