get_llms_txt
AI agents call get_llms_txt to retrieve information from MCP Package Hero without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data without modifying or deleting anything. No side effects are evident from the name. The 'get_' prefix is a strong signal of a read operation. Low severity because it only accesses metadata/text files with no blast radius to production systems or data integrity.
From the tool's definition Tool name 'get_llms_txt' suggests retrieval of a text file (likely an LLMs.txt manifest or metadata file). The empty description limits certainty, but the 'get_' prefix and context within a package information server indicate a read operation.
Attacks that exploit this kind of access
get_llms_txt. It is categorised as a Read tool in the MCP Package Hero MCP Server, which means it retrieves data without modifying state.
Register the MCP Package Hero MCP server in PolicyLayer and add a rule for get_llms_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 MCP Package Hero. Nothing to install.
get_llms_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 get_llms_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 get_llms_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.
get_llms_txt is provided by the MCP Package Hero MCP server (moinsen-dev/mcp-package-hero). 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 →