wolfram_mobile_query
AI agents call wolfram_mobile_query to retrieve information from Wolfram Alpha MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Wolfram Alpha queries retrieve computed results and mathematical solutions without creating, modifying, or deleting data on the user's system or Wolfram's service. This is a read-only lookup operation with no side effects beyond returning computed answers. Low severity because misuse would only return unwanted mathematical information, not compromise data or systems.
From the tool's definition Tool is part of Wolfram Alpha MCP Server which 'enables scientific computing, mathematical problem solving' through 'queries' to a third-party API.
Attacks that exploit this kind of access
wolfram_mobile_query. It is categorised as a Read tool in the Wolfram Alpha MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Wolfram Alpha MCP Server MCP server in PolicyLayer and add a rule for wolfram_mobile_query: 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 Wolfram Alpha MCP Server. Nothing to install.
wolfram_mobile_query 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 wolfram_mobile_query 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 wolfram_mobile_query. 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.
wolfram_mobile_query is provided by the Wolfram Alpha MCP Server MCP server (xiaomayisjh/wolfram-alpha-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 →