Log inSubmit server
Molio logo

Molio

Local-first MCP knowledge base for Markdown-backed research, writing, analysis, and knowledge graph workflows.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Molio

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "molio": {
      "command": "npx",
      "args": [
        "-y",
        "@molio/cli"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y @molio/cli

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 1d ago.

Overview

Molio MCP server connects AI agents to local knowledge spaces built from notes, documents, books, web pages, and other sources. It stores processed content as Markdown, then builds wiki-style indexes and knowledge graphs that agents can use for research, writing, answering, and analysis. Results can be written back into the knowledge space so later tasks have more context. Reach for Molio when you want agents to work over a private, evolving knowledge base instead of starting each conversation with no accumulated context.

Use cases

  • Build a searchable personal knowledge base from notes and documents
  • Research across books, PDFs, web pages, and an Obsidian vault
  • Write agent results back into a growing Markdown workspace
  • Explore relationships between entities through a knowledge graph
  • Import a ready-made domain knowledge base for question answering

Key features

  • Local Markdown-backed knowledge spaces
  • PDF and Office document processing with OCR and table reconstruction
  • Entity extraction, cross-links, indexes, and knowledge graphs
  • Resumable processing for million-word books
  • Obsidian vault access with read-only source files
  • Agent workflows for research, writing, answering, and analysis

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 2d ago via OSV.dev · @molio/cli (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars441Stargazers on the source repository.
npm downloads511Package downloads in the last 30 days.
Last commitTodayMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.

How Molio works

What Molio does

Molio provides a local-first knowledge layer for AI agents. It turns scattered personal material into a knowledge space that agents can read, query, work with, and extend. The underlying content remains on the local machine and is represented as Markdown, which keeps the stored data portable and editable.

The system is suited to collections that mix ordinary notes with larger or less structured sources. Supported material includes Markdown, TXT, HTML, CSV and other text files; PDFs; Word, PowerPoint, and Excel documents; images; web pages; and Obsidian vaults. Large books can be processed in chunks with resumable progress.

How it works

Text-based files can be read directly, while PDFs and Office documents pass through a document-processing workflow that performs layout analysis, OCR, and table reconstruction. Images are converted through OCR. Web content can be clipped, and an Obsidian vault can be opened in place with its original files treated as read-only.

Imported material is normalized into Markdown. A wiki engine then extracts entities and concepts, creating cross-links and layered indexes that form the knowledge graph. Agents such as Claude Code, Codex, Gemini CLI, and Qwen Code can work inside the resulting knowledge space. Their research, answers, analyses, and other outputs can be saved back as Markdown, allowing the collection to accumulate reusable results over time.

Molio also supports a web console with streaming agent output and can expose a knowledge base through WeChat. Ready-made knowledge bases are available for import, including resources covering literature, history, philosophy, traditional Chinese medicine, medicine, and AI engineering.

Tools and capabilities

  • Connect agents to local knowledge spaces containing accumulated Markdown content.
  • Import and process text files, PDFs, Office documents, images, web pages, and books.
  • Extract text from scanned material with OCR and preserve document structure and tables where supported.
  • Build wiki-style indexes, entity links, and visual knowledge graphs from the Markdown layer.
  • Support agent workflows for research, writing, answering questions, and analysis.
  • Deposit task results back into the knowledge base as Markdown.
  • Open existing Obsidian vaults without changing their original files.
  • Use prebuilt knowledge bases instead of preparing every collection from scratch.

Limitations and notes

PDF and Office conversion uses the bundled docling workflow. Its first conversion downloads the processing tool and roughly 500 MB of models; later conversions reuse the local cache.

Channel support varies. The web console supports text, images, files, and voice. WeChat and Feishu support text, images, and files, while some additional channel capabilities are planned rather than available.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Molio

Molio is an MCP server that connects AI agents to local personal knowledge spaces built from Markdown, documents, books, web pages, images, and Obsidian vaults. Its main capabilities cover importing and processing sources, exploring wiki links and knowledge graphs, supporting research and writing workflows, and saving agent results back as Markdown.

Install Molio through the @molio/cli package, which provides the MCP server and command-line interface.

Molio supports Markdown, TXT, HTML, CSV and other text files, along with PDFs, Word, PowerPoint, Excel, PNG, JPG, TIFF, web pages, and Obsidian vaults. PDFs and Office files are converted with layout analysis, OCR, and table reconstruction, while images undergo OCR.

Yes, Molio is designed to run on your machine and keep the knowledge base in local storage rather than sending it through a third-party Molio server. Imported and generated knowledge is represented as Markdown files, while model or agent providers may have separate data-handling policies.

Yes, Molio processes million-word books through chunked preprocessing and a digest pipeline with resumable progress. This approach lets interrupted work continue rather than requiring the entire book to be processed again.

Related MCP servers

All in Knowledge & Memory All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMolio AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/molio?style=directory)](https://allmcps.com/mcp/molio)
HTML Embed
<a href="https://allmcps.com/mcp/molio"><img src="https://allmcps.com/api/badge/molio?style=directory" alt="Molio on AllMCPs" /></a>