AI agents use via_task_done to create or update resources in Via — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Via environment.
This tool updates the status of an existing task to 'done', which is a reversible state change (the task record still exists and could theoretically be re-opened). It modifies data but does not delete or execute anything, making Write the most appropriate category. Severity is low as misuse would only incorrectly mark tasks as completed.
From the tool's definition Mark a Via task as done
Documented attack patterns abuse exactly the kind of access via_task_done gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Via, and nothing reaches the server without passing your rules. This is the rule we recommend for via_task_done:
{
"version": "1",
"default": "deny",
"tools": {
"via_task_done": {
"limits": [
{
"counter": "via_task_done_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}via_task_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 Via task as done. It is categorised as a Write tool in the Via MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Via MCP server in PolicyLayer and add a rule for via_task_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 Via. Nothing to install.
via_task_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 via_task_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 via_task_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.
via_task_done is provided by the Via MCP server (vektor-memory/via). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Via, 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 Via tools catalogued and risk-classified — across an index of 43,000+ MCP servers.