AI agents use mikey_math_export to create or update resources in Mcp Math — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Math environment.
This tool generates and exports Python code for use in notebooks—a Write operation (creates data artifact) rather than Execute (does not run code) or Destructive (output is reversible/non-destructive). The blast radius is minimal since exported code is inert text until executed by the user.
From the tool's definition Tool description states 'Export...as Python code', which creates/generates data (Python code artifact) that can be saved or copied.
Attacks that exploit this kind of access
Export the core math helpers as Python code for Jupyter notebooks. It is categorised as a Write tool in the Mcp Math MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Math MCP server in PolicyLayer and add a rule for mikey_math_export: 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 Mcp Math. Nothing to install.
mikey_math_export is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the mikey_math_export 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 mikey_math_export. 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.
mikey_math_export is provided by the Mcp Math MCP server (mikeybeez/mcp-math). 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 →