AI agents use save_project to create or update resources in CODESYS MCP Toolkit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CODESYS MCP Toolkit environment.
Save operations are Write category—they modify data (project files/state) in a manner that is reversible (can be undone via version control, previous saves, or rollback). This is less severe than Destructive (which would be irreversible deletion/overwrite).
From the tool's definition Tool name 'save_project' indicates persistence of project data modifications. Context shows this MCP server manages CODESYS V3 project lifecycle including creation, editing, and compilation. Saving project data reversibly modifies stored project state.
Documented attack patterns abuse exactly the kind of access save_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CODESYS MCP Toolkit, and nothing reaches the server without passing your rules. This is the rule we recommend for save_project:
{
"version": "1",
"default": "deny",
"tools": {
"save_project": {
"limits": [
{
"counter": "save_project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_project 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.
save_project. It is categorised as a Write tool in the CODESYS MCP Toolkit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CODESYS MCP Toolkit MCP server in PolicyLayer and add a rule for save_project: 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 CODESYS MCP Toolkit. Nothing to install.
save_project 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 save_project 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 save_project. 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.
save_project is provided by the CODESYS MCP Toolkit MCP server (johannespettersson80/codesys-mcp-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CODESYS MCP Toolkit, 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.
8 CODESYS MCP Toolkit tools catalogued and risk-classified — across an index of 43,000+ MCP servers.