AI agents call read_file_range to retrieve information from PSKit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves file contents within specified bounds without modifying, executing, or deleting data. It is a straightforward query operation analogous to 'head', 'tail', or 'sed' for viewing file segments. No write, execute, or destructive capabilities are present. The safety risk is minimal unless the server exposes highly sensitive files, but the tool itself poses no inherent risk of misuse.
From the tool's definition Tool name 'read_file_range' and description 'Read a specific line range from a file' indicate a read-only operation with no side effects. The emphasis on efficiency for large files reinforces that this is a retrieval operation.
Attacks that exploit this kind of access
Read a specific line range from a file — efficient for large files. It is categorised as a Read tool in the PSKit MCP Server, which means it retrieves data without modifying state.
Register the PSKit MCP server in PolicyLayer and add a rule for read_file_range: 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 PSKit. Nothing to install.
read_file_range 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 read_file_range 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 read_file_range. 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.
read_file_range is provided by the PSKit MCP server (nickalus12/pskit). 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 →