Register a new user request and plan its associated tasks.
AI agents use request_planning to create or update resources in MCP TaskManager — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP TaskManager environment.
This tool creates new request records and associated task plans, which are reversible operations (tasks can be deleted via delete_task, requests can be modified). It does not execute external code, delete data irreversibly, or move money.
From the tool's definition Tool description states 'Register a new user request and plan its associated tasks' — 'register' and 'plan' indicate creation and modification of data structures in the task queue system.
Documented attack patterns abuse exactly the kind of access request_planning gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP TaskManager, and nothing reaches the server without passing your rules. This is the rule we recommend for request_planning:
{
"version": "1",
"default": "deny",
"tools": {
"request_planning": {
"limits": [
{
"counter": "request_planning_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}request_planning 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.
Register a new user request and plan its associated tasks. It is categorised as a Write tool in the MCP TaskManager MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP TaskManager MCP server in PolicyLayer and add a rule for request_planning: 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 MCP TaskManager. Nothing to install.
request_planning 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 request_planning 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 request_planning. 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.
request_planning is provided by the MCP TaskManager MCP server (rudra-ravi/mcp-taskmanager). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP TaskManager, 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.
10 MCP TaskManager tools catalogued and risk-classified — across an index of 43,000+ MCP servers.