Create a fully-populated proposal in Plutio from a preset scaffold. Handles the multi-step flow transparently: POST the proposal, then POST each custom block linked to it, then reorder. Returns the created proposal with its block ids. Requires writes (PLUTIO_READ_ONLY=false).
AI agents use plutio_proposal_from_preset to create or update resources in Plutio — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Plutio environment.
This tool creates new proposals and associated custom blocks in the Plutio business platform. While creation is reversible (proposals can be deleted), the tool modifies state by creating business documents. It does not delete, overwrite irreversibly, move money, or execute arbitrary code—it specifically creates structured data.
From the tool's definition Tool description explicitly states 'Create a fully-populated proposal' and 'POST the proposal, then POST each custom block' with 'Requires writes (PLUTIO_READ_ONLY=false)'. The verb 'Create' combined with POST operations indicates data creation.
Documented attack patterns abuse exactly the kind of access plutio_proposal_from_preset gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Plutio, and nothing reaches the server without passing your rules. This is the rule we recommend for plutio_proposal_from_preset:
{
"version": "1",
"default": "deny",
"tools": {
"plutio_proposal_from_preset": {
"limits": [
{
"counter": "plutio_proposal_from_preset_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}plutio_proposal_from_preset 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.
Create a fully-populated proposal in Plutio from a preset scaffold. Handles the multi-step flow transparently: POST the proposal, then POST each custom block linked to it, then reorder. Returns the created proposal with its block ids. Requires writes (PLUTIO_READ_ONLY=false). It is categorised as a Write tool in the Plutio MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Plutio MCP server in PolicyLayer and add a rule for plutio_proposal_from_preset: 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 Plutio. Nothing to install.
plutio_proposal_from_preset 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 plutio_proposal_from_preset 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 plutio_proposal_from_preset. 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.
plutio_proposal_from_preset is provided by the Plutio MCP server (thecreativelabs/plutio-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Plutio, 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.
16 Plutio tools catalogued and risk-classified — across an index of 43,000+ MCP servers.