Analyze project structure, organization, and architecture type
AI agents call analyze_project_structure to retrieve information from CodeBase Optimizer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and evaluates information about project structure and architecture but does not create, modify, delete, or execute any code or operations. It is a read-only analysis tool that queries and reports on existing codebase properties. The low severity reflects that misuse would only expose information about code organization without enabling destructive or executing actions.
From the tool's definition Tool 'analyze_project_structure' performs analysis and evaluation of project structure, organization, and architecture type.
Attacks that exploit this kind of access
Analyze project structure, organization, and architecture type. It is categorised as a Read tool in the CodeBase Optimizer MCP Server, which means it retrieves data without modifying state.
Register the CodeBase Optimizer MCP server in PolicyLayer and add a rule for analyze_project_structure: 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 CodeBase Optimizer. Nothing to install.
analyze_project_structure 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 analyze_project_structure 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 analyze_project_structure. 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.
analyze_project_structure is provided by the CodeBase Optimizer MCP server (liadgez/codebase-optimizer-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 →