AI agents use upload_data to create or update resources in SAS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SAS MCP Server environment.
The tool writes data to a persistent storage system (CAS table) which modifies the data state. While not destructive (data can be replaced or removed), it is a write operation that could introduce incorrect or malicious data into analytical systems. In a SAS Viya environment, this could impact downstream analyses and reports.
From the tool's definition Tool description states 'Upload CSV data into a CAS table' — this creates or modifies data in the CAS (Cloud Analytic Services) system. Upload operations are reversible through deletion or replacement.
Documented attack patterns abuse exactly the kind of access upload_data gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SAS MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for upload_data:
{
"version": "1",
"default": "deny",
"tools": {
"upload_data": {
"limits": [
{
"counter": "upload_data_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}upload_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.
Upload CSV data into a CAS table. It is categorised as a Write tool in the SAS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SAS MCP Server MCP server in PolicyLayer and add a rule for upload_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 SAS MCP Server. Nothing to install.
upload_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 upload_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 upload_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.
upload_data is provided by the SAS MCP Server MCP server (sassoftware/sas-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SAS 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.
27 SAS MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.