This record as markdown: /tools/todos/save-command-alias.md
What save_command_alias does on Todos
AI agents use save_command_alias to create or update resources in Todos, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.
Why save_command_alias is rated Medium
This tool creates or modifies command aliases in project-local configuration, making it a reversible Write operation. While command aliases could potentially be misused to obfuscate malicious commands, the core action is configuration modification, not execution or deletion.
From the tool's definition Tool name explicitly states 'save' and description confirms 'Save or update', which are Write operations that create or modify data. The alias configuration is reversible and can be updated or removed later.
Attacks that exploit this kind of access
The rule that runs save_command_alias safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Todos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For save_command_alias, this is the rule to start with:
save_command_alias stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Todos, apply this rule, and every save_command_alias call is checked against it from then on.
Questions about save_command_alias
Save or update a project-local command alias. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todos MCP server in PolicyLayer and add a rule for save_command_alias: 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 Todos. Nothing to install.
save_command_alias 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 save_command_alias 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 save_command_alias. 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.
save_command_alias is provided by the Todos MCP server (@hasna/todos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Todos, and thousands of servers like it.
This server
Across the catalogue