Read and return text from New.txt with file info.
AI agents call read_txt to retrieve information from Claude File Management Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs data retrieval (reading a text file) with no side effects. It neither modifies, executes, deletes, nor creates any files. The operation is limited to a specific file (New.txt) and returns its contents and metadata. This is a classic Read category tool with minimal blast radius.
From the tool's definition Tool name is 'read_txt' and description states 'Read and return text from New.txt with file info.' This is a read-only operation that retrieves file contents without modification.
Attacks that exploit this kind of access
Read and return text from New.txt with file info. It is categorised as a Read tool in the Claude File Management Server MCP Server, which means it retrieves data without modifying state.
Register the Claude File Management Server MCP server in PolicyLayer and add a rule for read_txt: 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 Claude File Management Server. Nothing to install.
read_txt 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_txt 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_txt. 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_txt is provided by the Claude File Management Server MCP server (vipin1000/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 →