AI agents use completeTodo to create or update resources in Cloudflare MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cloudflare MCP environment.
This tool modifies existing data (marking a todo as completed) in a reversible manner—the state can be changed back. It is not destructive (the data persists), not financial, and not code execution. It fits squarely into the Write category. The severity is low because the blast radius of accidental misuse is minimal; completing todos has no external impact and the operation is easily undoable.
From the tool's definition Tool name 'completeTodo' and description 'Mark a task as completed in your todo list' indicate a modification operation that updates task state.
Documented attack patterns abuse exactly the kind of access completeTodo gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cloudflare MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for completeTodo:
{
"version": "1",
"default": "deny",
"tools": {
"completeTodo": {
"limits": [
{
"counter": "completetodo_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}completeTodo 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.
Mark a task as completed in your todo list. It is categorised as a Write tool in the Cloudflare MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cloudflare MCP server in PolicyLayer and add a rule for completeTodo: 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 Cloudflare MCP. Nothing to install.
completeTodo 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 completeTodo 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 completeTodo. 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.
completeTodo is provided by the Cloudflare MCP server (shashankboosi/cloudflare-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cloudflare MCP, 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.
7 Cloudflare MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.