get_tool_definition
AI agents call get_tool_definition to retrieve information from Code Execution MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to retrieve and return tool definitions or metadata—a non-destructive query operation. However, without an explicit description, confidence is moderated. The broader server context (sandboxed code execution environment) suggests this retrieves information about available capabilities.
From the tool's definition Tool name 'get_tool_definition' suggests retrieval of metadata or documentation about tools. Sibling tools include 'list_*' and 'read_*' operations, contextually supporting a Read classification. No description provided, limiting evidence specificity.
Attacks that exploit this kind of access
get_tool_definition. It is categorised as a Read tool in the Code Execution MCP MCP Server, which means it retrieves data without modifying state.
Register the Code Execution MCP server in PolicyLayer and add a rule for get_tool_definition: 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 Code Execution MCP. Nothing to install.
get_tool_definition 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 get_tool_definition 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 get_tool_definition. 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.
get_tool_definition is provided by the Code Execution MCP server (marc-shade/code-execution-mcp). 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 →