Read-only search and discovery for the international llms.txt directory maintained by llmsmap.me.
Scored across 2 tools
The two tools have clearly distinct purposes: one lists the entire catalog, the other searches by name or URL. There is no overlap in functionality, so an agent can easily select the right tool.
Both tools follow a consistent verb_noun pattern: 'list_catalog' and 'search_catalog' use lowercase snake_case with a clear action and object. The naming is predictable and uniform.
With only 2 tools, the server feels thin for a directory service, which typically requires more operations (e.g., get details, pagination, filtering). However, for a simple read-only catalog, the count is borderline acceptable.
The tool set covers the core operations of listing and searching a catalog, which is the stated purpose. Minor gaps include lack of a 'get_single_site' tool or explicit pagination controls, but agents can work around these with the existing tools.
Get approved sites in the llmsmap.ru catalog with llms.txt URLs, token counts, and metadata.
Inputs: limit.
Search the llmsmap.ru catalog by product name or URL.
Inputs: query (required), limit.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Search verified AI agents, MCP servers, and native llms.txt documentation endpoints.
Any site's llms.txt: find the covering index, read its linked docs as markdown, search sections.
Generate, validate, and deep-crawl /llms.txt and /llms-full.txt files for AI agents.
LLM API discovery: access conditions, dated costs, sampled checks and keyless configs. Read-only.
Add one secure layer between your agents and this server.
