Portable MCP knowledge delivery
MCPOrb: The PDF for
AI-native knowledge delivery.
Package product docs, service playbooks, and expert knowledge into portable MCP Orbs that run locally inside AI tools.
Package product docs, service playbooks, and expert knowledge into portable MCP Orbs that run locally inside AI tools.
Like a PDF, but for AI clients. Knowledge, index, configuration, and local Web UI — all in one portable Orb.
One Orb file contains your knowledge, search index, configuration, and runtime. Deliver it like a PDF — no cloud setup, no database, no API key required.
Orbs run entirely on the user's machine. No data upload. No vendor lock-in. No compliance risk. Your knowledge stays where you put it.
Every Orb includes a local Web UI. See every document, chunk, source, and search result. No black box — open the browser and verify.
Works with Claude Desktop, Cursor, VS Code, and any MCP-compatible AI client. One config line and your knowledge is available as a search_knowledge tool.
MCPOrbBuilder turns your PDF or Markdown documents into a self-contained Orb. The Orb runs locally, exposes a search_knowledge MCP tool, and includes a local Web UI for inspection.
# Build an Orb from a PDF mcporb build your-docs.pdf --name my-orb # Inspect the result mcporb inspect target/orbs/my-orb # Test a query mcporb test-query target/orbs/my-orb \ "What is the onboarding process?" # Launch Web UI mcporb run target/orbs/my-orb --open # Claude Desktop config { "mcpServers": { "my-orb": { "command": "/path/to/my-orb", "args": ["--stdio-only"] } } }
MCPOrb is for B2B teams that need to package and deliver knowledge — not just store it.
Turn product docs, API references, and migration guides into AI-ready delivery assets. Give customers an Orb they can use in their AI tools instead of searching static docs.
Package onboarding guides, FAQ, and troubleshooting playbooks as Orbs. Reduce support load and improve developer self-service success rates.
Deliver client-specific knowledge packs alongside project deliverables. Package methodology and expertise as a reusable AI assistant.
Distribute knowledge to internal teams without uploading sensitive data to external SaaS. Maintain data boundaries while enabling AI-assisted workflows.
The MCPOrb Runtime is open source. Inspect the code, understand exactly what runs on your machine or your customer's machine. No black box.
Orbs run entirely locally. No API keys, no data upload, no vendor lock-in, no compliance risk. Your knowledge stays where you put it.
The local Web UI shows every chunk, source document, page number, and search score. You can verify every answer before it reaches your users.
RAG helps you answer questions.
MCPOrb helps you ship knowledge as a product asset — portable, inspectable, and deliverable to customers, partners, and teams.
Ship knowledge with confidence — only the right people can unlock it.
Like an encrypted PDF, you can password-protect an Orb before distribution. But unlike a PDF, the password is entered through the Orb's dedicated Web UI — never in the AI chat. This keeps the password out of the conversation history and ensures sensitive content stays protected.
Browse published Orbs, upload your own, or download and license the Builder — all self-serve at MCPOrbStore.
Search published Orbs by keyword, tag, or built-in retrieval method. Download a ready-to-run Orb for your OS.
Upload your own Orb and we validate it automatically. Every successful upload mints a free 90-day trial code.
Download the desktop Builder for macOS, Windows, or Linux and activate it — $99/yr, one device per license.
MCPOrb implements the Model Context Protocol (MCP) standard. It works with Claude Desktop, Cursor, VS Code, and any MCP-compatible AI client. Add one line to your MCP config and your Orb's knowledge is available as a search_knowledge tool.
No. Orbs run entirely on the user's machine. There is no data upload, no cloud dependency, no API keys, and no vendor lock-in. Your knowledge stays where you put it — local execution only.
Uploading documents sends your data to a third-party cloud. MCPOrb keeps everything local. It also packages your knowledge as a structured, inspectable, portable file — not just a one-time conversation context. You can distribute Orbs to customers, partners, and teams like a PDF.
MCPOrb runs on macOS (Apple Silicon and Intel), Linux (Ubuntu 20.04+, Debian), and Windows x64. No GPU required. The runtime is lightweight and works on a standard laptop — from a MacBook Air M2 to a repurposed Linux machine.
We're working with a small group of B2B software teams, consulting firms, and internal AI platform teams to build the first Orbs from real documents.
We'll run a free 30-minute Orb Fit Assessment to determine whether your content is a good fit, what the Orb would look like, and what success would mean for your team.
✅ Request received! We'll be in touch within 2 business days.
In the meantime, check out the public demo on GitHub.