Mark a todo as completed. Call this when a user explicitly says they
AI agents use mark-todo-completed to create or update resources in BeeMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your BeeMCP environment.
This tool updates the state of a todo reversibly (completion status can typically be toggled back), making it a Write operation rather than Destructive. The impact is moderate because it affects personal task management data, but the change is not irreversible and the blast radius is confined to the user's own todo list. Confidence is high despite the truncated description because the name and intent are clear.
From the tool's definition Tool name is 'mark-todo-completed' and description states 'Mark a todo as completed', which modifies the status of an existing todo item.
Documented attack patterns abuse exactly the kind of access mark-todo-completed gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and BeeMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for mark-todo-completed:
{
"version": "1",
"default": "deny",
"tools": {
"mark-todo-completed": {
"limits": [
{
"counter": "mark-todo-completed_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mark-todo-completed 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 todo as completed. Call this when a user explicitly says they. It is categorised as a Write tool in the BeeMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bee MCP server in PolicyLayer and add a rule for mark-todo-completed: 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 BeeMCP. Nothing to install.
mark-todo-completed 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 mark-todo-completed 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 mark-todo-completed. 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.
mark-todo-completed is provided by the Bee MCP server (okgodoit/beemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 19 BeeMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
19 BeeMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.