AI agents invoke test_aptos_contract to trigger actions in Aptos. 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.
This tool runs tests via the Aptos CLI, which executes code/commands on the system. CLI execution can have side effects depending on the test setup (network interactions, state changes on testnets, resource consumption). It goes beyond mere reading since it actively invokes the CLI to run contract tests.
From the tool's definition "Test an Aptos Move contract using the Aptos CLI"
Attacks that exploit this kind of access
Test an Aptos Move contract using the Aptos CLI. It is categorised as a Execute tool in the Aptos MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Aptos MCP server in PolicyLayer and add a rule for test_aptos_contract: 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 Aptos. Nothing to install.
test_aptos_contract 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 test_aptos_contract 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 test_aptos_contract. 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.
test_aptos_contract is provided by the Aptos MCP server (tlazypanda/aptos-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 →