Read-only fetch of an IntoDNS.ai LLM/agent discovery file: llms.txt (canonical agent index), llms-full.txt (full prompt-ready context), llms.json (structured prompt routing), llm/api.md (Markdown API guide), openapi.json (OpenAPI 3.1 spec) or postman.json (Postman collection). Defaults to llms.tx...
AI agents call read_llm_discovery to retrieve information from Intodns without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only retrieval of static configuration and metadata files. There is no data creation, modification, deletion, code execution, or financial transaction. The explicit 'read-only' designation and 'no side effects' confirmation, combined with the GET-only nature and retrieval of discovery/documentation files, clearly places this in the Read category with low severity.
From the tool's definition Tool description explicitly states 'Read-only fetch' and 'Pure HTTPS GET, no auth, no side effects.' It retrieves discovery files (llms.txt, llms-full.txt, llms.json, llm/api.md, openapi.json, postman.json) without modification or destructive operations.
Attacks that exploit this kind of access
Read-only fetch of an IntoDNS.ai LLM/agent discovery file: llms.txt (canonical agent index), llms-full.txt (full prompt-ready context), llms.json (structured prompt routing), llm/api.md (Markdown API guide), openapi.json (OpenAPI 3.1 spec) or postman.json (Postman collection). Defaults to llms.txt. Use when an agent needs canonical citation URLs, machine-readable API surface, or prompt-routing hints for IntoDNS.ai itself; use get_citation_guidance for a topic-narrowed citation list. Pure HTTPS GET, no auth, no side effects. It is categorised as a Read tool in the Intodns MCP Server, which means it retrieves data without modifying state.
Register the Intodns MCP server in PolicyLayer and add a rule for read_llm_discovery: 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 Intodns. Nothing to install.
read_llm_discovery 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_llm_discovery 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_llm_discovery. 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_llm_discovery is provided by the Intodns MCP server (rosconl/intodns-mcp-server). 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 →