AI agents invoke math_with_context to trigger actions in Study. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool performs mathematical operations with additional side effects: context tracking and progress reporting. These side effects (tracking state, reporting progress) go beyond pure calculation and suggest it triggers external operations or mutates state, placing it in Execute rather than Read. Severity is medium because misuse could pollute tracking/logging systems, though the core math operation is low-risk.
From the tool's definition "Perform a mathematical operation with context tracking and progress reporting"
Attacks that exploit this kind of access
Perform a mathematical operation with context tracking and progress reporting. It is categorised as a Execute tool in the Study MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Study MCP server in PolicyLayer and add a rule for math_with_context: 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 Study. Nothing to install.
math_with_context is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the math_with_context 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 math_with_context. 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.
math_with_context is provided by the Study MCP server (lucs1590/study-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 →