Read a specific range of lines from a file by line number. Use find_in_file first to locate keywords and get their line numbers, then use this to read just the relevant section. Only works within allowed directories.
AI agents call read_lines to retrieve information from FilesystemMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves file content without altering it. The description confirms it is a read-only operation that extracts specific line ranges from files. The restriction to allowed directories further limits risk. No side effects, data modification, execution, or destructive capabilities are present.
From the tool's definition Tool name 'read_lines' and description explicitly states it 'Read[s] a specific range of lines from a file by line number' with no modification capability. Operates 'within allowed directories' only.
Attacks that exploit this kind of access
Read a specific range of lines from a file by line number. Use find_in_file first to locate keywords and get their line numbers, then use this to read just the relevant section. Only works within allowed directories. It is categorised as a Read tool in the FilesystemMCP MCP Server, which means it retrieves data without modifying state.
Register the Filesystem MCP server in PolicyLayer and add a rule for read_lines: 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 FilesystemMCP. Nothing to install.
read_lines 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_lines 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_lines. 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_lines is provided by the Filesystem MCP server (rijadalisic/filesystemmcp). 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 →