AI agents use create_aptos_indexer to create or update resources in Aptos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Aptos environment.
This tool creates a new project structure (indexer configuration, boilerplate code) which is a reversible write operation. It does not execute arbitrary code against live systems, delete data, or move funds. The blast radius is medium because misconfiguration of an indexer could cause downstream data processing issues, but the operation itself is reversible (the project can be deleted or modified).
From the tool's definition Tool name 'create_aptos_indexer' and description states it 'Creates a new Aptos indexer project based on the example processor' — the word 'Creates' indicates a write operation that generates new project files/resources.
Attacks that exploit this kind of access
Creates a new Aptos indexer project based on the example processor. It is categorised as a Write tool in the Aptos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Aptos MCP server in PolicyLayer and add a rule for create_aptos_indexer: 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.
create_aptos_indexer 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 create_aptos_indexer 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 create_aptos_indexer. 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.
create_aptos_indexer 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 →