AI agents use import_data to create or update resources in PocketBase MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PocketBase MCP Server environment.
Importing data creates or modifies records within a collection, which is a reversible write operation. It does not delete data (hence not Destructive), does not execute arbitrary code (hence not Execute), and is not financial. The severity is medium rather than high because imports can be reversed through other operations, though large imports could have significant blast radius if misused.
From the tool's definition Tool name 'import_data' and description 'Import data into a collection' indicate creation/modification of data. The PocketBase MCP Server context shows this is a database operation that adds or modifies records in a collection.
Documented attack patterns abuse exactly the kind of access import_data gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PocketBase MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for import_data:
{
"version": "1",
"default": "deny",
"tools": {
"import_data": {
"limits": [
{
"counter": "import_data_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} import_data stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Import data into a collection. It is categorised as a Write tool in the PocketBase MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the PocketBase MCP Server MCP server in PolicyLayer and add a rule for import_data: 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 PocketBase MCP Server. Nothing to install.
import_data 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 import_data 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 import_data. 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.
import_data is provided by the PocketBase MCP Server MCP server (mrwyndham/pocketbase-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PocketBase MCP Server, 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.
24 PocketBase MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.