How to use Leapable

Your AI now has a photographic memory.

Leapable connects to Claude Code, Cursor, and other AI agents. Ask your AI in plain English — it creates databases, ingests files, and searches them for you. You never leave your AI chat.

15 minutes to your first query. No code required. Every step below has a copy-paste prompt.

1. Install Leapable (one click)

Download the installer for your OS. Double-click it. That's the whole thing.

Download installer

What the installer does for you — automatically

You don't need to install Docker, edit config files, run terminal commands, or configure MCP. The installer handles every piece:

Detects Docker, installs it if missing. If Docker Desktop isn't on your machine, the installer downloads and sets it up silently.
Pulls the Leapable server image. ~7 MB code layer on top of a cached 3.5 GB base that already includes all AI models (no runtime downloads, ever).
Starts the MCP server on localhost:4100. Bundled embedder (nomic-embed-text-v1.5) + reranker (ms-marco-MiniLM) run locally. Your text files never leave your machine.
Auto-configures 9 AI clients. If Claude Code, Cursor, Cline, Continue, Claude Desktop, Warp, Zed, VS Code, or Windsurf is installed on your machine, the installer registers Leapable as an MCP server in their configs. You don't touch a JSON file.
Creates a persistent data volume. Your databases survive image updates. The installer uses a named Docker volume so Leapable upgrades never wipe your data.
Auto-updates in the background. New versions pull silently through the Docker socket. You never see a "please update" modal.

After the installer finishes, restart any running AI client (Claude Code, Cursor, etc.) so it picks up the new MCP server. That's the only manual step.

2. Verify your AI can see it

Open your AI and ask:

Use leapable_status to check that the Leapable MCP is healthy, and list any databases I already have.

If your AI replies with status: ok and ~164 tools available, you're done. If it can't find any Leapable tools, jump to Troubleshooting.

3. Create your first database

Think of a database as a folder your AI can read instantly. One database per topic is a good default — "my-research-papers", "company-wiki", "contracts-2026", etc.

1Ask your AI to create a database:

Create a new leapable database called "research-papers". Give it the description "Academic papers I'm reading for my thesis on quantum networks" and tag it with "academic" and "physics".

2Your AI will call leapable_db_create behind the scenes. Confirm it worked:

Show me all my local leapable databases.

Your AI will run leapable_db_list and show you a table with document counts, sizes, and last-accessed timestamps.

Pro tip: The description is what other creators' databases get matched against when someone searches. Write it like a one-sentence pitch, not a folder note. Good: "Alex Hormozi's sales + offer frameworks from his book and podcast." Bad: "my docs".

4. Add files to it

Leapable supports PDFs, DOCX, Markdown, plain text, images (via OCR), audio transcripts, and more. Just tell your AI where the files are.

From a folder on your disk

Select the leapable database "research-papers", then ingest every .pdf and .md file from ~/Documents/thesis/papers — recursively into subfolders. When done, process anything pending.

Specific files

Ingest these three files into the "research-papers" database: ~/Downloads/entanglement-2024.pdf, ~/Downloads/decoherence-review.pdf, ~/notes/chapter-3-draft.md. Process them after.

Watch the progress

Show me the processing status of the research-papers database. How many docs are pending vs. complete?

Text files (.md, .txt) process instantly on your machine. PDFs and images use cloud OCR (1 credit per 5 pages, rounded up — a 24-page PDF is 5 credits). Everything else — chunking, embedding, search indexing — happens locally for free.

5. Search & ask questions

This is where it gets magical. Your AI can semantic-search (meaning-based), keyword-search (exact-word-based), or hybrid-search (best of both) across everything you've ingested.

Ask a question, get cited answers

In my "research-papers" database, what do different authors say about decoherence in superconducting qubits? Give me the best 5 passages with citations.

Exact-phrase lookup

Search research-papers for the exact phrase "T1 relaxation time". Show the 10 most relevant hits and tell me which documents they came from.

Compare two documents

Compare the two papers on entanglement swapping in my research-papers database. What do they agree on? Where do they disagree? Cite the specific sections.

Rolled-up summary of the whole corpus

Summarize what's in my research-papers database overall. Themes, how many docs, what areas are well-covered vs. thin. Keep it under 300 words.

Every answer carries citations. When your AI answers, it quotes the source document + page + exact chunk. Click any citation in the dashboard to open the original document at that page.

6. Navigate & organize

Everything has a web view. Go to your workspace to browse visually — or keep asking your AI.

List what's in a database

Show me the first 20 documents in research-papers, sorted by most recent. Include file name, page count, and status.

Group similar documents

Cluster the documents in research-papers by topic. How many clusters did it find? Show me the top themes in each.

Add tags

Tag the research-papers database with "thesis-2026" and "chapter-3-source".

Export everything

Export research-papers as a single JSON file I can back up.

7. Search across databases

Have five databases? Ask the question to all of them at once. Your AI routes the query to whichever ones are likely relevant.

Across all my leapable databases, find everything I have on "risk management in early-stage startups". Rank by relevance, show which database each hit came from.

Under the hood your AI calls leapable_search_cross_db — semantic similarity across everything you've ingested.

Browse creator databases on the marketplace

The marketplace lists databases other creators have published — medicine, legal, finance, specific author catalogs, etc. You can query them too (1 credit per query).

Search the Leapable marketplace for databases about "sales frameworks". List the top 5 — who made them, what's inside, and how much per query.

8. Share or sell your knowledge

Any database you've built can be published to the marketplace. Keep it free, set a per-query credit price, or bolt on a monthly paywall. Leapable keeps 30%, creators keep 70%.

Publish as-is

Publish my research-papers database to the Leapable marketplace. Free for anyone to query. Don't add a paywall.

Publish with a paywall

Publish my trading-strategies database with a $29/month paywall. 2 credits per query. Give it a catchy creator headline for the marketplace listing.

Manage your creator profile + Stripe payouts from Creator Studio.

9. Ready-to-use AI prompts

Copy-paste these into Claude Code / Cursor / Cline. Replace {placeholders} with your own values.

Researcher workflow

Create a leapable database called "{topic}-research" tagged with "research". Ingest every PDF in ~/Downloads/papers/. Once processed, tell me how many docs, how many pages, average quality score, and any files that failed OCR.

Literature review

For my {topic}-research database: (1) cluster all docs by sub-topic, (2) pick the 3 clusters with the most docs, (3) write a 200-word literature-review paragraph for each cluster, citing specific passages.

Contract review

Ingest ~/Documents/contracts/vendor-2026-Q2.pdf into a database called "vendor-contracts". After processing, find every clause about indemnity, liability caps, and termination rights. Quote exact language and tell me the page.

Meeting notes knowledge-base

Ingest every file in ~/Dropbox/meetings/ into a database called "team-meetings". Once done, I'll ask you for decisions, action items, and follow-ups by person.

Code documentation index

Create a leapable database "api-docs" and ingest every .md file under ~/repos/{project}/docs/. I want to ask it questions about our internal APIs.

Due-diligence dossier

Ingest everything in ~/diligence/{company}/ — PDFs, spreadsheets, PPTs — into a database called "{company}-diligence". Then: (1) summarize their financial position, (2) list every risk factor mentioned anywhere, (3) compare their stated valuation against the assumptions in their financial model.

Personal archive / second brain

Walk ~/Dropbox/notes/ recursively and ingest everything into a database called "second-brain". After that I want to ask it what I was thinking about on specific dates, or pull quotes from my old journal entries by topic.

10. AI client setup details

Leapable speaks the Model Context Protocol (MCP), so anything that supports MCP can talk to it.

Claude Code

claude mcp add leapable --transport http http://localhost:4100/mcp — then restart.

Cursor

Settings → MCP → Add Server → paste the JSON from section 1.

Cline / Continue

Both support MCP. Point at http://localhost:4100/mcp in their MCP config.

Claude Desktop

Settings → Developer → MCP Servers. Stdio transport via docker exec -i leapable node dist/bin.js.

11. Troubleshooting

My AI says it can't see leapable tools

1. Make sure the Leapable Docker container is running: curl http://localhost:4100/health — should return {"status":"ok","tools_count":164}.

2. Restart your AI client after adding the MCP server.

3. Ask your AI: "list the tool namespaces you have available" — you should see a leapable_* namespace.

Ingestion looks stuck

Ask: "leapable retry failed documents in the {name} database, then process pending". That resets stuck items and restarts OCR.

Search returns nothing

Ask: "use leapable_db_stats on {name} to tell me how many chunks and embeddings exist". If chunks=0 the documents haven't been processed yet. If embeddings=0 the GPU/CPU embedder couldn't reach the model.

I need help that's not here

Email support@leapable.ai or check the FAQ.

Ready to query your own knowledge?

Every plan includes monthly credits. Cancel anytime. 50% of unused credits roll over.

See plans