get_lua_source
AI agents call get_lua_source to retrieve information from Electra One without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get' prefix strongly indicates a read operation that retrieves data (Lua source code) with no side effects. Despite the empty description reducing confidence slightly, the naming pattern and context within a widget/preset development server make it clear this is a query/fetch operation.
From the tool's definition Tool name 'get_lua_source' indicates retrieval of source code. No description provided, but the verb 'get' and context of an Electra One MK2/Mini development server suggest this retrieves existing Lua source code without modification.
Attacks that exploit this kind of access
get_lua_source. It is categorised as a Read tool in the Electra One MCP Server, which means it retrieves data without modifying state.
Register the Electra One MCP server in PolicyLayer and add a rule for get_lua_source: 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 Electra One. Nothing to install.
get_lua_source is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_lua_source 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 get_lua_source. 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.
get_lua_source is provided by the Electra One MCP server (roomi-fields/electra-one-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →