Generate human-understandable explanation of a decision path. Shows which factors contributed most and why.
AI agents call explain_decision to retrieve information from Deep Thinker without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only introspection and reporting tool. It analyzes and presents reasoning that already exists in the server's thought graph without altering state, running external operations, or affecting other systems. The blast radius of misuse is minimal—an AI agent could request misleading explanations, but cannot corrupt data or trigger external effects through this tool alone.
From the tool's definition The tool 'explain_decision' generates explanations and shows factors and reasoning—it retrieves and presents existing analysis without modifying data, executing external code, or causing side effects.
Documented attack patterns abuse exactly the kind of access explain_decision gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Deep Thinker, and nothing reaches the server without passing your rules. This is the rule we recommend for explain_decision:
{
"version": "1",
"default": "deny",
"tools": {
"explain_decision": {}
}
}explain_decision is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Generate human-understandable explanation of a decision path. Shows which factors contributed most and why. It is categorised as a Read tool in the Deep Thinker MCP Server, which means it retrieves data without modifying state.
Register the Deep Thinker MCP server in PolicyLayer and add a rule for explain_decision: 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 Deep Thinker. Nothing to install.
explain_decision 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 explain_decision 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 explain_decision. 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.
explain_decision is provided by the Deep Thinker MCP server (nachosystems/deep-thinker). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Deep Thinker, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 Deep Thinker tools catalogued and risk-classified — across an index of 43,000+ MCP servers.