Documentation on AgentCore Code Interpreter for executing code in agents.
AI agents call agentcore_code_interpreter 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.
Despite the name referencing code execution, this tool provides *documentation* about the Code Interpreter feature — it retrieves and returns informational content rather than executing any code itself. It is a read-only reference tool similar to the other sibling documentation tools (agentcore_gateway, agentcore_identity, etc.).
From the tool's definition Documentation on AgentCore Code Interpreter for executing code in agents
Attacks that exploit this kind of access
Documentation on AgentCore Code Interpreter for executing code in 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_code_interpreter: 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_code_interpreter 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_code_interpreter 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_code_interpreter. 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_code_interpreter 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 →