filter by nation/tier/class/type/name
AI agents call search_tanks to retrieve information from WoT Blitz MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves game data about tanks without modifying, deleting, or executing external operations. It is purely informational, allowing users to filter and discover tank statistics from the game's local file data. This is a read-only operation with negligible security risk.
From the tool's definition Tool description specifies filtering and searching (search_tanks) by tank attributes (nation/tier/class/type/name). The server explicitly states it 'retrieves...game data' with 'no side effects' for tools like search and get operations.
Attacks that exploit this kind of access
filter by nation/tier/class/type/name. It is categorised as a Read tool in the WoT Blitz MCP Server MCP Server, which means it retrieves data without modifying state.
Register the WoT Blitz MCP Server MCP server in PolicyLayer and add a rule for search_tanks: 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 WoT Blitz MCP Server. Nothing to install.
search_tanks 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 search_tanks 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 search_tanks. 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.
search_tanks is provided by the WoT Blitz MCP Server MCP server (revenant30102000/wotblitz-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 →