read_text_file
Read the complete contents of a file from the file system as text. Handles various text encodings and provides detailed error messages if the file cannot be read. Use this tool when you need to examine the contents of a single file. Use the 'head' parameter to read only the first N lines of a fil...
This record as markdown: /tools/filesystem/read-text-file.md
What read_text_file does on Filesystem
AI agents call read_text_file to retrieve information from Filesystem without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
head | number | — | If provided, returns only the first N lines of the file |
path | string | Yes | |
tail | number | — | If provided, returns only the last N lines of the file |
Parameters from the server's own tool schema.
Why read_text_file is rated Low
This tool retrieves and queries file contents with no side effects or modifications. It performs a read-only operation on the filesystem. The low severity reflects the minimal risk—an AI agent using this tool can only view data within permitted directories, with no ability to create, modify, delete, or execute anything.
From the tool's definition Tool name is 'read_text_file' and description states 'Read the complete contents of a file from the file system as text.' It provides options to read with 'head' and 'tail' parameters for partial reads.
Risk signalsAccepts file system path (path)
Attacks that exploit this kind of access
The rule that runs read_text_file safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Filesystem, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For read_text_file, this is the rule to start with:
read_text_file is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Filesystem, apply this rule, and every read_text_file call is checked against it from then on.
Questions about read_text_file
Read the complete contents of a file from the file system as text. Handles various text encodings and provides detailed error messages if the file cannot be read. Use this tool when you need to examine the contents of a single file. Use the 'head' parameter to read only the first N lines of a file, or the 'tail' parameter to read only the last N lines of a file. Operates on the file as text regardless of extension. Only works within allowed directories. It is categorised as a Read tool in the Filesystem MCP Server, which means it retrieves data without modifying state.
read_text_file accepts 3 parameters: head, path, tail. Required: path. The full parameter table on this page comes from the server's own tool schema.
Register the Filesystem MCP server in PolicyLayer and add a rule for read_text_file: 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 Filesystem. Nothing to install.
read_text_file 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_text_file 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_text_file. 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_text_file is provided by the Filesystem MCP server (@modelcontextprotocol/server-filesystem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Filesystem, and thousands of servers like it.
This server
Across the catalogue