AI agents invoke ultra-plan to trigger actions in Ultra MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool orchestrates multi-step planning workflows involving revisions and branches, suggesting it triggers external AI model calls and potentially modifies or creates planning artifacts across multiple steps. It goes beyond simple read/query behavior. The description is vague about side effects, but 'revisions and branches' implies state changes or structured outputs being created/modified, placing it in Execute.
From the tool's definition Multi-step feature planning with revisions and branches
Documented attack patterns abuse exactly the kind of access ultra-plan gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ultra MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for ultra-plan:
{
"version": "1",
"default": "deny",
"tools": {
"ultra-plan": {
"limits": [
{
"counter": "ultra-plan_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}ultra-plan stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Multi-step feature planning with revisions and branches. It is categorised as a Execute tool in the Ultra MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ultra MCP server in PolicyLayer and add a rule for ultra-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 Ultra MCP. Nothing to install.
ultra-plan is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ultra-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 ultra-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.
ultra-plan is provided by the Ultra MCP server (realmikechong/ultra-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 30 Ultra MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
30 Ultra MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.