AI agents use add-todo to create or update resources in Things — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Things environment.
Creating todos is a reversible write operation that modifies application state. Severity is medium because bulk or automated todo creation could clutter the productivity system and create noise, but todos can be deleted and the impact is limited to the user's task list without external side effects or data destruction.
From the tool's definition Tool name 'add-todo' indicates creation of new todo items; server description confirms it 'create[s], update[s], and manage[s] todos' via Things app integration. No description provided for this specific tool, but context establishes write operations.
Documented attack patterns abuse exactly the kind of access add-todo gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Things, and nothing reaches the server without passing your rules. This is the rule we recommend for add-todo:
{
"version": "1",
"default": "deny",
"tools": {
"add-todo": {
"limits": [
{
"counter": "add-todo_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add-todo 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.
Free to start. No card required.
add-todo. It is categorised as a Write tool in the Things MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Things MCP server in PolicyLayer and add a rule for 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 Things. Nothing to install.
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 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 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.
add-todo is provided by the Things MCP server (jimfilippou/things-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Things, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Things tools catalogued and risk-classified — across an index of 43,000+ MCP servers.