AI agents use mark-done to create or update resources in Akiflow MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Akiflow MCP Server environment.
This tool performs a reversible modification of task data by updating a task's completion status. It does not execute code, delete data irreversibly, involve financial transactions, or trigger external operations beyond the task management system. The action can be undone by marking the task as incomplete again, placing it in the Write category.
From the tool's definition Tool description states 'Mark a task as completed' which modifies task status. The tool name 'mark-done' and description indicate a state change operation on existing data (task completion status).
Documented attack patterns abuse exactly the kind of access mark-done gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Akiflow MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for mark-done:
{
"version": "1",
"default": "deny",
"tools": {
"mark-done": {
"limits": [
{
"counter": "mark-done_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mark-done 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. It is categorised as a Write tool in the Akiflow MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Akiflow MCP Server MCP server in PolicyLayer and add a rule for mark-done: 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 Akiflow MCP Server. Nothing to install.
mark-done 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-done 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-done. 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-done is provided by the Akiflow MCP Server MCP server (shrimpwtf/akiflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Akiflow MCP Server, 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.
22 Akiflow MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.