Salt Md
by
Provides docs, databases, and realtime collaboration within a single binary, allowing AI agents and humans to share the same workspace with unified permissions.
Salt Md Overview
What is Salt Md about?
Salt Md delivers a self‑hosted workspace where documentation, structured data, and real‑time editing coexist. It runs as a single Go binary backed by one SQLite file, enabling both people and AI agents (Claude, ChatGPT, Cursor, etc.) to operate on the same pages, databases, and permissions.
How to use Salt Md?
- Quick install:
curl -fsSL https://raw.githubusercontent.com/saltmd/salt.md/main/install.sh | shdownloads, installs, starts the service, and shows the access URL. Re‑run to upgrade. - Docker:
docker run -d -p 8420:8420 -v salt-data:/data ghcr.io/saltmd/salt.md:latestruns the server in a container. - Configuration: No external database, cache, or object store is required. The binary stores data in a single SQLite file plus an optional uploads directory. Reverse proxy, TLS, and backups are covered in the self‑hosting guide.
- Access: Open the printed address in a browser, or connect any MCP‑compatible client (agents, CLI tools) to
/mcp.
Key Features
- Pages: Create, edit, move, duplicate, trash, and restore with a block editor (slash menu, checklists, code, tables, callouts, diagrams).
- Databases/Collections: Turn any page into a typed collection (select, date, person, relation, rollup, formula, etc.) and view it as table, board, list, gallery, calendar, timeline, or form.
- Search: Full‑text search across pages and OCR‑extracted PDF content, respecting the same permission checks as humans.
- Bulk Imports: Import any JSON source directly without routing data through an agent.
- Comments & Activity Log: Append‑only note trail, threaded comments, and page history.
- Presence: Live cursors show which person or agent is editing a page.
- Permission Isolation: Agents cannot create/delete accounts, issue tokens, manage backups, or change instance settings. Permissions are enforced per workspace.
- Export/Import: Markdown files, CSVs, and Notion export imports are supported.
- Single‑File Persistence: One SQLite file plus an
uploads/folder. - Cross‑Platform: Linux/macOS (amd64 & arm64) and Windows (amd64).
Use Cases
- Team Knowledge Base: Centralize documentation, SOPs, and meeting notes with live collaboration.
- AI‑Assisted Workflow: Let agents generate database entries, summarize information, or create pages while humans review and continue work.
- Project Planning: Use boards, calendars, and timelines to track tasks, milestones, and resources.
- Data Catalog: Store structured data (e.g., inventory, contacts) in collections with rich property types and query them via the UI or MCP API.
- Self‑Hosted Notion Alternative: Replace cloud‑based note‑taking tools with a privacy‑first, open‑source solution.
FAQ
Q: How do I back up my data?
A: Stop the server, copy the SQLite file and the uploads/ directory, then restart.
Q: Can I run Salt Md on Windows? A: Yes, a static Windows amd64 binary is provided.
Q: How do I upgrade? A: For the binary install, re‑run the install script; for Docker, pull the newer image and restart the container.
Q: What license is it under? A: AGPL‑3.0 – you may use, modify, and run it at work, but must publish changes if you provide the service over a network.
Q: How are AI agents authenticated? A: Agents receive a credential that carries the same access rights as the associated user; they cannot exceed those permissions.
Q: Do I need external services like PostgreSQL or Redis? A: No. All data lives in a single SQLite file; the binary includes the embedded frontend.
Q: Where can I find the documentation? A: The full docs are at https://salt.md/wiki/ and are version‑checked against the codebase.
Salt Md's README
Quickstart
curl -fsSL https://raw.githubusercontent.com/saltmd/salt.md/main/install.sh | sh
One command downloads the binary for your platform, installs it, starts it and
prints the address to open. On a Linux server it sets itself up as a systemd
service, and running it again upgrades it. No curl on the machine?
wget -qO- … | sh does the same.
Or with Docker:
docker run -d -p 8420:8420 -v salt-data:/data ghcr.io/saltmd/salt.md:latest
There is nothing else to install: no database server, no cache, no object store. Reverse proxies, TLS and backups are in the self-hosting guide.
People and agents in the same place
An agent is asked to organise the launch notes. A page appears, a database is created, the rows fill in. A person opens the same board a second later and carries on. Same pages, same permissions, same history.
Connect Claude, ChatGPT, Codex, Cursor, Gemini CLI or any other MCP client to
/mcp and it works on the workspace you use:
- Pages: create, edit, move, duplicate, trash and restore
- Databases: create them, change the schema, add and query rows, set up views
- Search with the same permission checks a person gets
- Bulk imports from any JSON source, without the content passing through the agent
- Comments, and an append-only note trail on every page
- Presence: the page shows which agent is working on it, before you start typing
And a list it cannot touch. No agent can create or delete accounts, issue tokens, take or restore a backup, change instance settings or decide who is in a workspace, and the server tells every agent that connects. A credential carries its person's access and never more, every workspace decides what agents may do there, and the activity log keeps their changes apart from yours.
MCP tools · Agent access · Permissions
A whole workspace
Moving in? Markdown files, CSVs and a Notion export import from the same menu.
Under the hood
One Go process, built with CGO_ENABLED=0: a static binary with a pure-Go
SQLite driver and the frontend embedded. No PostgreSQL, no Redis, no object
store, no separate collaboration server.
- Install: one binary,
install.sh, or the Docker image - Data: one SQLite file plus an uploads directory
- Update: swap the binary or pull the image, restart
- Backup: stop, copy two paths, start
- Platforms: Linux and macOS on amd64 and arm64, Windows on amd64
The desktop app for macOS and Linux is a window onto a server you run, not a second copy of the product.
Documentation
salt.md/wiki covers every screen, every property type,
every tool an agent can call and every setting on the server. It is written next
to this code and checked against it on every build: a tool name that no longer
exists, an API path that is not a route or a screenshot whose screen has changed
fails the build. Every page is also plain Markdown at the same address with
.md on the end, indexed for agents at
/wiki/llms.txt.
Contributing
Issues and pull requests are welcome. Pull requests need a signed CLA; CONTRIBUTING.md says what that means and why it exists. Security reports go to dev@salt.md, not to a public issue: see SECURITY.md.
License
AGPL-3.0. Use it, run it at work, change it. If you offer it to others over a network, publish your changes.
The components salt.md is built on, with their licences in full, are in
THIRD-PARTY-NOTICES.md. A running instance serves the
same list at /licenses.
Salt Md Reviews
Login Required
Please log in to share your review and rating for this MCP.
Similar MCP Servers like Salt Md
Explore related MCPs that share similar capabilities and solve comparable challenges
Memory
Officialby modelcontextprotocol
A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.
Cognee
by topoteretes
Provides dynamic memory for AI agents through modular ECL (Extract, Cognify, Load) pipelines, enabling seamless integration with graph and vector stores using minimal code.
Basic Memory
by basicmachines-co
Enables persistent, local‑first knowledge management by allowing LLMs to read and write Markdown files during natural conversations, building a traversable knowledge graph that stays under the user’s control.
Agentset
by agentset-ai
Provides an open‑source platform to build, evaluate, and ship production‑ready retrieval‑augmented generation (RAG) and agentic applications, offering end‑to‑end tooling from ingestion to hosting.
Obsidian Model Context Protocol
by smithery-ai
Provides read and search capabilities for Markdown notes in an Obsidian vault for Claude Desktop and other MCP clients.
Mcp Server Chatsum
by chatmcp
Summarize chat messages by querying a local chat database and returning concise overviews.
Minima
by dmayboroda
Provides on‑premises conversational retrieval‑augmented generation (RAG) with configurable Docker containers, supporting fully local execution, ChatGPT‑based custom GPTs, and Anthropic Claude integration.
Mcp Server Qdrant
Officialby qdrant
Provides a Model Context Protocol server that stores and retrieves semantic memories using Qdrant vector search, acting as a semantic memory layer.
MCP Memory Service
by doobidoo
Provides a universal memory service with semantic search, intelligent memory triggers, OAuth‑enabled team collaboration, and multi‑client support for Claude Desktop, Claude Code, VS Code, Cursor and over a dozen AI applications.