API-first, with an MCP server for your AI tools
Wire clean document conversion into your pipeline or your agents. One call turns any file or URL into AI-ready Markdown.
Convert a URL in one call:
curl -X POST https://api.llmtomd.com/v1/convert \
-H "X-API-Key: $LLMTOMD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url": "https://example.com/report"}'
# → { "job_id": "...", "status": "queued" }
# Poll /v1/jobs/{id}, then GET /v1/documents/{id}?format=mdREST API
Convert files and URLs, poll jobs, fetch Markdown, search, extract fields, and ask questions — all over a clean, typed HTTP API.
MCP server
Connect LLMtoMD to Claude — Desktop, Claude.ai, or the API — so Claude can convert links, search your documents, and answer from them on demand. Set it up in Settings → Connect to Claude.
RAG export
Get chunked JSONL with embeddings for any document — a drop-in for your vector database, LangChain, or LlamaIndex.
Push ingestion
POST a file straight to /ingest, or register a watched source so new objects in a storage prefix convert and index automatically.
API keys & rate limits
Scoped API keys per organization, with rate-limit headers and usage metering you can build against.
Credits & metering
Transparent per-conversion credit costs surfaced in the API, so you can predict and control spend programmatically.
Connect LLMtoMD to your AI tools
One MCP server, every assistant — use your documents inside Claude, ChatGPT, Cursor, the OpenAI API, LangChain, and LlamaIndex. Sign in for apps; an API key for code.
See all integrationsBuild on clean document data
Get an API key and convert your first document free — then connect it to your pipeline or your agents over REST or MCP.