AI agents use onpe_bootstrap_snapshot to create or update resources in Onpe — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Onpe environment.
This tool imports/loads a local snapshot into a SQLite database, which is a write operation that creates or populates data in the local database. It is reversible (data can be re-imported or cleared) and does not execute arbitrary code or delete data irreversibly. Severity is medium because it modifies the local database state that other tools depend on for queries.
From the tool's definition Importa snapshot local de onpescraper hacia SQLite para acelerar consultas
Attacks that exploit this kind of access
Importa snapshot local de onpescraper hacia SQLite para acelerar consultas (sin bloquear fallback live API). It is categorised as a Write tool in the Onpe MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Onpe MCP server in PolicyLayer and add a rule for onpe_bootstrap_snapshot: 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 Onpe. Nothing to install.
onpe_bootstrap_snapshot 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 onpe_bootstrap_snapshot 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 onpe_bootstrap_snapshot. 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.
onpe_bootstrap_snapshot is provided by the Onpe MCP server (oscarzamora/onpe-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 →