AI agents use gsd_add_todo to create or update resources in Gsd — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gsd environment.
This tool creates new data (todo entries) in the GSD project management system. It is reversible (todos can typically be deleted or marked as obsolete), so it does not rise to Destructive. It has no financial impact and does not execute external commands. It is a straightforward Write operation that modifies project state.
From the tool's definition Tool description states 'Capture idea or task as todo' — this is a create/add operation that modifies the GSD project state by adding a new todo item. The verb 'capture' combined with 'add' in the tool name indicates a data creation action.
Attacks that exploit this kind of access
Capture idea or task as todo from current conversation. It is categorised as a Write tool in the Gsd MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gsd MCP server in PolicyLayer and add a rule for gsd_add_todo: 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 Gsd. Nothing to install.
gsd_add_todo is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the gsd_add_todo 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 gsd_add_todo. 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.
gsd_add_todo is provided by the Gsd MCP server (m0-ar/gsd-mcp-server). 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 →