Get a 500-word markdown summary of the project: domains, entry points, tech stack, key patterns, and size metrics. Use this as your first call when entering a new repo.
AI agents call get_architecture to retrieve information from Carto MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about project structure without modifying any data or executing code. It is informational and observational in nature, matching the Read category definition: 'retrieves or queries data; no side effects.' The low severity reflects that misuse only exposes existing information about the codebase rather than risking unauthorized modifications or operations.
From the tool's definition Tool description states it retrieves a 'summary' of project architecture and metadata (domains, entry points, tech stack, patterns, metrics).
Documented attack patterns abuse exactly the kind of access get_architecture gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Carto MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_architecture:
{
"version": "1",
"default": "deny",
"tools": {
"get_architecture": {}
}
}get_architecture is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get a 500-word markdown summary of the project: domains, entry points, tech stack, key patterns, and size metrics. Use this as your first call when entering a new repo. It is categorised as a Read tool in the Carto MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Carto MCP Server MCP server in PolicyLayer and add a rule for get_architecture: 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 Carto MCP Server. Nothing to install.
get_architecture 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_architecture 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_architecture. 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_architecture is provided by the Carto MCP Server MCP server (theanshsonkar/carto). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 22 Carto MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
22 Carto MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.