Expand one decision to its full detail. Recall surfaces (get_relevant_context, get_project_decisions, get_session_decisions) return decisions summary-only to keep context lean. Use this to pull the full reasoning for a single decision you want to open — pay for detail only where you ask for it. I...
AI agents call get_decision_detail to retrieve information from Kawa Code MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays existing decision information without modifying, creating, deleting, executing operations, or moving resources. It is a read-only query that fetches detailed information about a previously stored decision record. The explicit mention of 'pay for detail only where you ask for it' confirms this is a retrieval mechanism rather than an action-triggering tool.
From the tool's definition Tool name 'get_decision_detail' and description states it 'Expand one decision to its full detail' and 'pull the full reasoning for a single decision'.
Attacks that exploit this kind of access
Expand one decision to its full detail. Recall surfaces (get_relevant_context, get_project_decisions, get_session_decisions) return decisions summary-only to keep context lean. Use this to pull the full reasoning for a single decision you want to open — pay for detail only where you ask for it. Inputs: - \. It is categorised as a Read tool in the Kawa Code MCP MCP Server, which means it retrieves data without modifying state.
Register the Kawa Code MCP server in PolicyLayer and add a rule for get_decision_detail: 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 Kawa Code MCP. Nothing to install.
get_decision_detail 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_decision_detail 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_decision_detail. 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_decision_detail is provided by the Kawa Code MCP server (kawacode-ai/kawa.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 →