AI agents call get_plugin_params to retrieve information from Flai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a passive information retrieval operation — listing parameter metadata from an existing plugin. No data is created, modified, deleted, or executed. The operation has no side effects beyond returning current state information. This aligns squarely with the 'Read' category for query/list operations.
From the tool's definition Tool name 'get_plugin_params' and description 'List all automatable parameters of the plugin in a channel' indicate a read-only query operation that retrieves plugin parameter information without modifying or executing any actions.
Attacks that exploit this kind of access
List all automatable parameters of the plugin in a channel. It is categorised as a Read tool in the Flai MCP Server, which means it retrieves data without modifying state.
Register the Flai MCP server in PolicyLayer and add a rule for get_plugin_params: 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 Flai. Nothing to install.
get_plugin_params 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_plugin_params 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_plugin_params. 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_plugin_params is provided by the Flai MCP server (kaupau/flai-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 →