LLMtoMD turns your docs into clean, AI-ready Markdown and serves them to Cursor, Claude Code, and any MCP client so your coding agent retrieves your spec instead of forgetting it.
Overview
LLMtoMD — the memory layer for AI coding agents.
Convert any document — PDF, DOCX, slides, spreadsheets, images, audio, even whole websites — into clean, structured Markdown, then expose it over MCP so your agent can search your FRDs, specs, and API docs on demand instead of re-reading (or forgetting) them.
On a real 50-page spec, answering one question via retrieval used ~97% fewer tokens than holding the whole document in context — and returned the exact, cited requirement.
Tools
This server is OAuth-secured (it serves each user's private library), so the live Tools tab needs sign-in to enumerate. The tools it exposes:
- list_documents / get_document — browse and read your library
- search_documents — semantic search across your docs
- ask_documents — RAG answer with citations
- convert_url — turn any web page into Markdown
- save_note — write a decision or spec back into the knowledge base
- list_collections — focus on one project
Connect (OAuth — no token to paste)
- Cursor / VS Code: add the server URL
https://mcp.llmtomd.com/mcp - Claude Code:
claude mcp add --transport http llmtomd https://mcp.llmtomd.com/mcp - Also works with Claude, Antigravity, and via API key for OpenAI / LangChain / LlamaIndex.
- Full guides → https://llmtomd.com/integrations
Try it
- "List my LLMtoMD documents."
- "Using my documents, what are the authentication requirements?"
- "Convert https://example.com/article into Markdown and summarize it."
Free tier included (MCP on every plan) → https://llmtomd.com
Server Config
{
"mcpServers": {
"llmtomd": {
"url": "https://mcp.llmtomd.com/mcp"
}
}
}