Update an existing plan with incremental operations. Pass an array of operations to insert, delete, or replace nodes. Operations are applied in order with smooth animations. After calling this, call get_approval to confirm changes with the user.
AI agents use request_plan_update to create or update resources in Overture — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Overture environment.
This tool creates or modifies plan data (nodes, structure) reversibly. While 'delete' appears in the description, the context shows it deletes UI plan nodes (which can be recreated via subsequent updates or plan resets), not irreversible data destruction. The mandatory approval gate (get_approval) mitigates risk but does not change the underlying Write category.
From the tool's definition Tool description states it can 'insert, delete, or replace nodes' in an existing plan, which are reversible modifications (not destructive deletions from a database).
Documented attack patterns abuse exactly the kind of access request_plan_update gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Overture, and nothing reaches the server without passing your rules. This is the rule we recommend for request_plan_update:
{
"version": "1",
"default": "deny",
"tools": {
"request_plan_update": {
"limits": [
{
"counter": "request_plan_update_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}request_plan_update 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 with incremental operations. Pass an array of operations to insert, delete, or replace nodes. Operations are applied in order with smooth animations. After calling this, call get_approval to confirm changes with the user. It is categorised as a Write tool in the Overture MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Overture MCP server in PolicyLayer and add a rule for request_plan_update: 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 Overture. Nothing to install.
request_plan_update 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_plan_update 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_plan_update. 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_plan_update is provided by the Overture MCP server (sixhq/overture). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 Overture tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 Overture tools catalogued and risk-classified — across an index of 42,500+ MCP servers.