Multiply two matrices. Input as nested arrays [[row1],[row2],...]. Column count of A must match row count of B. Max 100x100. Example: matrix_multiply([[1,2],[3,4]], [[5,6],[7,8]]) -> [[19,22],[43,50]]
AI agents call matrix_multiply to retrieve information from MCP Calc Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool takes two matrix inputs and returns their product. It is a stateless mathematical calculation with no writes, deletions, financial transactions, or external executions. The max size constraint (100x100) limits blast radius further. Classified as Read (pure computation/query).
From the tool's definition 'Multiply two matrices' — performs a pure mathematical computation on provided input arrays with no side effects, no data storage, and no external operations.
Documented attack patterns abuse exactly the kind of access matrix_multiply gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Calc Tools, and nothing reaches the server without passing your rules. This is the rule we recommend for matrix_multiply:
{
"version": "1",
"default": "deny",
"tools": {
"matrix_multiply": {}
}
} matrix_multiply 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.
Multiply two matrices. Input as nested arrays [[row1],[row2],...]. Column count of A must match row count of B. Max 100x100. Example: matrix_multiply([[1,2],[3,4]], [[5,6],[7,8]]) -> [[19,22],[43,50]]. It is categorised as a Read tool in the MCP Calc Tools MCP Server, which means it retrieves data without modifying state.
Register the MCP Calc Tools MCP server in PolicyLayer and add a rule for matrix_multiply: 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 Calc Tools. Nothing to install.
matrix_multiply 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 matrix_multiply 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 matrix_multiply. 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.
matrix_multiply is provided by the MCP Calc Tools MCP server (nbiish/mcp-calc-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Calc Tools, 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.
22 MCP Calc Tools tools catalogued and risk-classified — across an index of 43,000+ MCP servers.