store_files
Store uploaded files. Receives file objects with name, size, type, data (base64).
This record as markdown: /tools/agent-jail-mcp/store-files.md
What store_files does on Agent Jail
AI agents use store_files to create or update resources in Agent Jail, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Jail environment.
Why store_files is rated Medium
The tool creates/stores new files on the server by accepting uploaded file objects with base64-encoded data. This is a write operation (creating data), reversible in principle (files could be deleted), with medium severity as it could be misused to store malicious content or large amounts of data.
From the tool's definition 'Store uploaded files. Receives file objects with name, size, type, data (base64).'
Attacks that exploit this kind of access
The rule that runs store_files safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Agent Jail, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For store_files, this is the rule to start with:
store_files 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Agent Jail, apply this rule, and every store_files call is checked against it from then on.
Questions about store_files
Store uploaded files. Receives file objects with name, size, type, data (base64). It is categorised as a Write tool in the Agent Jail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agent Jail MCP server in PolicyLayer and add a rule for store_files: 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 Agent Jail. Nothing to install.
store_files 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 store_files 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 store_files. 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.
store_files is provided by the Agent Jail MCP server (idiscoord13-sketch/agent-jail-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Agent Jail, and thousands of servers like it.
This server
Across the catalogue