append_run_command
Append a command entry and optional stdout/stderr to a run record (redacted).
This record as markdown: /tools/todos/append-run-command.md
What append_run_command does on Todos
AI agents use append_run_command 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 append_run_command is rated Medium
This tool appends/writes data (command entries and output) to an existing run record. It is a reversible write operation that adds log/audit data to a record rather than executing commands or deleting anything. Severity is low as it only modifies task run records within a task management system.
From the tool's definition Append a command entry and optional stdout/stderr to a run record
Attacks that exploit this kind of access
The rule that runs append_run_command 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 append_run_command, this is the rule to start with:
append_run_command 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 append_run_command call is checked against it from then on.
Questions about append_run_command
Append a command entry and optional stdout/stderr to a run record (redacted). 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 append_run_command: 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.
append_run_command 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 append_run_command 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 append_run_command. 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.
append_run_command 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