AI agents use update_plan to create or update resources in Valkey MCP Task Management Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Valkey MCP Task Management Server environment.
Update operations are Write-category because they create or modify data reversibly. The modification can be undone by applying a counter-update. This is less severe than Destructive (which irreversibly removes data) or Execute (which runs arbitrary operations).
From the tool's definition Tool name is 'update_plan' with description 'Update an existing plan'. The verb 'update' indicates modification of existing data in a reversible manner.
Documented attack patterns abuse exactly the kind of access update_plan gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Valkey MCP Task Management Server, and nothing reaches the server without passing your rules. This is the rule we recommend for update_plan:
{
"version": "1",
"default": "deny",
"tools": {
"update_plan": {
"limits": [
{
"counter": "update_plan_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_plan 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.
Update an existing plan. It is categorised as a Write tool in the Valkey MCP Task Management Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Valkey MCP Task Management Server MCP server in PolicyLayer and add a rule for update_plan: 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 Valkey MCP Task Management Server. Nothing to install.
update_plan 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 update_plan 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 update_plan. 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.
update_plan is provided by the Valkey MCP Task Management Server MCP server (jbrinkman/valkey-ai-tasks). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Valkey MCP Task Management 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.
17 Valkey MCP Task Management Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.