Zwróć ostatnie TODO zapisane przez dev_todo.
AI agents call dev_get_todos to retrieve information from RPG Ledger 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 retrieves saved development TODO items. It has no side effects, does not modify data, does not execute operations, and does not involve financial transactions. It is a pure read operation on internal development state.
From the tool's definition Tool name 'dev_get_todos' and description 'Zwróć ostatnie TODO zapisane przez dev_todo' (Return the latest TODOs saved by dev_todo) indicate a retrieval operation that returns previously stored development notes without modifying or executing anything.
Attacks that exploit this kind of access
Zwróć ostatnie TODO zapisane przez dev_todo. It is categorised as a Read tool in the RPG Ledger MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RPG Ledger MCP Server MCP server in PolicyLayer and add a rule for dev_get_todos: 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 RPG Ledger MCP Server. Nothing to install.
dev_get_todos 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 dev_get_todos 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 dev_get_todos. 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.
dev_get_todos is provided by the RPG Ledger MCP Server MCP server (sepa79/rpg-ledger-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 →