AI agents use close to create or update resources in MCP-BPMN Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP-BPMN Server environment.
This tool performs a reversible state modification—closing and clearing the current diagram context. While it clears data from the active session, it does not permanently delete saved files or irreversibly destroy data (which would be Destructive). The action is reversible in that a user could reopen or reload a diagram.
From the tool's definition Tool named 'close' with description 'Close the current diagram and clear the context' modifies state by terminating the current working context and clearing diagram data from memory/session.
Documented attack patterns abuse exactly the kind of access close gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-BPMN Server, and nothing reaches the server without passing your rules. This is the rule we recommend for close:
{
"version": "1",
"default": "deny",
"tools": {
"close": {
"limits": [
{
"counter": "close_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}close 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.
Close the current diagram and clear the context. It is categorised as a Write tool in the MCP-BPMN Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP-BPMN Server MCP server in PolicyLayer and add a rule for close: 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 MCP-BPMN Server. Nothing to install.
close 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 close 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 close. 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.
close is provided by the MCP-BPMN Server MCP server (oisee/mcp-bpmn). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-BPMN Server, 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.
41 MCP-BPMN Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.