Get the file contents given a file id, and a file-system location to save to
AI agents call downloadFile to retrieve information from RSpace MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward read operation that fetches and outputs file data. No data is created, modified, deleted, or destroyed. While the tool writes to local storage (the provided file-system location), this is the intended output mechanism for a read operation, not a write to the RSpace system itself.
From the tool's definition Tool retrieves file contents given a file ID and save location. The description uses 'Get' and 'download', indicating data retrieval without modification or deletion of source data.
Attacks that exploit this kind of access
Get the file contents given a file id, and a file-system location to save to. It is categorised as a Read tool in the RSpace MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RSpace MCP Server MCP server in PolicyLayer and add a rule for downloadFile: 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 RSpace MCP Server. Nothing to install.
downloadFile is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the downloadFile 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 downloadFile. 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.
downloadFile is provided by the RSpace MCP Server MCP server (richarda23/rspace-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 →