AI agents call reactor_timing to retrieve information from Baselings without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves predictive game state information (reactor timing and clustering detection) to inform decision-making. It has no side effects on game data, user assets, or blockchain state. The most severe impact of misuse would be poor strategic decisions based on timing predictions, which constitutes low risk.
From the tool's definition Tool description states it 'Predict[s] when reactors will fire next' and 'Shows time until each reactor can fire' — purely informational queries with no modification, deletion, or financial transaction capability.
Attacks that exploit this kind of access
Predict when reactors will fire next. Shows time until each reactor can fire, detects clustering (multiple reactors near-ready), and flags. It is categorised as a Read tool in the Baselings MCP Server, which means it retrieves data without modifying state.
Register the Baselings MCP server in PolicyLayer and add a rule for reactor_timing: 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 Baselings. Nothing to install.
reactor_timing 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 reactor_timing 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 reactor_timing. 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.
reactor_timing is provided by the Baselings MCP server (jimbo530/baselings-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 →