Given a natural-language intent, returns files to touch, domains affected, blast radius, and similar patterns.
AI agents call get_change_plan 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.
get_change_plan reads and analyzes codebase metadata to provide planning information. It does not execute code, modify files, delete data, or commit financial transactions. While it plans changes, it only returns analytical data about what could be changed, not performing any actual modifications. This is fundamentally a Read operation—querying live codebase structure for informational purposes.
From the tool's definition Tool returns analysis of files, domains, blast radius, and patterns based on intent. The description uses 'returns' indicating data retrieval with no modification operations.
Documented attack patterns abuse exactly the kind of access get_change_plan 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_change_plan:
{
"version": "1",
"default": "deny",
"tools": {
"get_change_plan": {}
}
}get_change_plan 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.
Given a natural-language intent, returns files to touch, domains affected, blast radius, and similar patterns. 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_change_plan: 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_change_plan 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_change_plan 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_change_plan. 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_change_plan 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.