Search object keys inside the current draft payload.
AI agents call local_draft_search_keys to retrieve information from Cascade Cms without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches for keys within an existing draft payload, returning information about the structure. It does not create, modify, delete, or execute any operations—it only retrieves metadata about the draft. The operation is read-only with no side effects, and the blast radius of misuse is minimal (limited information disclosure about draft structure).
From the tool's definition Tool name 'search_keys' and description 'Search object keys inside the current draft payload' indicate a read-only query operation that retrieves or inspects data structure without modification.
Attacks that exploit this kind of access
Search object keys inside the current draft payload. It is categorised as a Read tool in the Cascade Cms MCP Server, which means it retrieves data without modifying state.
Register the Cascade Cms MCP server in PolicyLayer and add a rule for local_draft_search_keys: 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 Cascade Cms. Nothing to install.
local_draft_search_keys 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 local_draft_search_keys 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 local_draft_search_keys. 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.
local_draft_search_keys is provided by the Cascade Cms MCP server (kuklaph/cascade-cms-mcp-server). 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 →