demo_save_actions
Write the rehearsed steps to disk. This file is the input to web-perform.mjs,
This record as markdown: /tools/demoday-claude-plugin/demo-save-actions.md
What demo_save_actions does on Demoday Claude Plugin
AI agents use demo_save_actions to create or update resources in Demoday Claude Plugin, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Demoday Claude Plugin environment.
Why demo_save_actions is rated Medium
Creates or modifies files on disk; reversible but could overwrite existing scripts if agent misuses paths.
From the tool's definition Write the rehearsed steps to disk. File is input to web-perform.mjs
Attacks that exploit this kind of access
The rule that runs demo_save_actions safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Demoday Claude Plugin, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For demo_save_actions, this is the rule to start with:
demo_save_actions 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Demoday Claude Plugin, apply this rule, and every demo_save_actions call is checked against it from then on.
Questions about demo_save_actions
Write the rehearsed steps to disk. This file is the input to web-perform.mjs,. It is categorised as a Write tool in the Demoday Claude Plugin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Demoday Claude Plugin MCP server in PolicyLayer and add a rule for demo_save_actions: 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 Demoday Claude Plugin. Nothing to install.
demo_save_actions 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 demo_save_actions 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 demo_save_actions. 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.
demo_save_actions is provided by the Demoday Claude Plugin MCP server (mrieck/demoday-claude-plugin). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Demoday Claude Plugin, and thousands of servers like it.
This server
Across the catalogue