AI agents use start_planning to create or update resources in Software Planning Tool — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Software Planning Tool environment.
This tool initiates a new planning session, which involves creating state/data on the server. It is a write operation (creates a new session) with low severity since it only initializes a planning context and does not modify existing data, execute code, or have financial implications. Misuse would at worst create spurious planning sessions.
From the tool's definition 'Start a new planning session with a goal' — creates a new planning session, which is a reversible write/create operation
Documented attack patterns abuse exactly the kind of access start_planning gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Software Planning Tool, and nothing reaches the server without passing your rules. This is the rule we recommend for start_planning:
{
"version": "1",
"default": "deny",
"tools": {
"start_planning": {
"limits": [
{
"counter": "start_planning_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}start_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.
Start a new planning session with a goal. It is categorised as a Write tool in the Software Planning Tool MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Software Planning Tool MCP server in PolicyLayer and add a rule for start_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 Software Planning Tool. Nothing to install.
start_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 start_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 start_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.
start_planning is provided by the Software Planning Tool MCP server (nighttrek/software-planning-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Software Planning Tool tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Software Planning Tool tools catalogued and risk-classified — across an index of 42,500+ MCP servers.