upload_to_file_store
AI agents use upload_to_file_store to create or update resources in Gpal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gpal environment.
The tool uploads data to a file store, which is a reversible write operation. It creates or modifies files/data without permanently deleting them. Severity is medium because uncontrolled file uploads could consume storage, overwrite important files, or introduce malicious content, but the operation is reversible through deletion or replacement.
From the tool's definition Tool name 'upload_to_file_store' indicates creation or modification of data in a file store. Sibling tools include 'create_file_store' and 'delete_file_store', suggesting this tool writes or modifies persisted data. Description is empty, reducing confidence.
Documented attack patterns abuse exactly the kind of access upload_to_file_store gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gpal, and nothing reaches the server without passing your rules. This is the rule we recommend for upload_to_file_store:
{
"version": "1",
"default": "deny",
"tools": {
"upload_to_file_store": {
"limits": [
{
"counter": "upload_to_file_store_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}upload_to_file_store 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.
upload_to_file_store. It is categorised as a Write tool in the Gpal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gpal MCP server in PolicyLayer and add a rule for upload_to_file_store: 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 Gpal. Nothing to install.
upload_to_file_store 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 upload_to_file_store 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 upload_to_file_store. 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.
upload_to_file_store is provided by the Gpal MCP server (tobert/gpal). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gpal, 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.
19 Gpal tools catalogued and risk-classified — across an index of 43,000+ MCP servers.