AI agents use messages_create to create or update resources in Propresenter — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Propresenter environment.
The tool creates a new message artifact within ProPresenter, which is a reversible write operation. While it modifies the presentation state, the action can be undone (typical for presentation software). Severity is medium rather than low because unintended message creation during a live presentation could cause disruption, but it is not destructive and does not delete or execute arbitrary code.
From the tool's definition Tool name 'messages_create' combined with description 'Create a new message' indicates data creation/modification capability in ProPresenter presentation software.
Documented attack patterns abuse exactly the kind of access messages_create gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Propresenter, and nothing reaches the server without passing your rules. This is the rule we recommend for messages_create:
{
"version": "1",
"default": "deny",
"tools": {
"messages_create": {
"limits": [
{
"counter": "messages_create_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}messages_create 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 new message. It is categorised as a Write tool in the Propresenter MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Propresenter MCP server in PolicyLayer and add a rule for messages_create: 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 Propresenter. Nothing to install.
messages_create 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 messages_create 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 messages_create. 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.
messages_create is provided by the Propresenter MCP server (@alxpark/propresenter-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Propresenter, 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.
177 Propresenter tools catalogued and risk-classified — across an index of 43,000+ MCP servers.