Syncpen
About
A markdown knowledge base your AI reads, writes, and organizes — a memory in plain files you can actually open and correct (not an opaque vector store), with every agent edit signed and yours to approve.
Details
- Author
- airbuzz
- Downloads
- 328
- Categories
- AI, Other, Knowledge Base, Productivity
Jump to
- 19 tools including read, search, create, update
- Suggest-edit with accept/reject workflow
- Commenting, folder organization, and publishing
- Edits are signed for user approval
- Works with Claude Code, Cursor, claude.ai, Cowork
- Free account available at syncpen.io
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
SyncpenCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Add the Syncpen MCP server to your MCP configuration with the command npx -y syncpen-mcp and set the SYNCPEN_API_KEY environment variable. Obtain an API key from the Syncpen settings page, then confirm connectivity with /mcp. Once configured, you can invoke any of the 19 tools to search, read, create, update, suggest edits, comment, organize folders, and publish to CMS platforms.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"syncpen": {
"syncpen": {
"command": "npx",
"args": [
"-y",
"syncpen-mcp"
],
"env": {
"SYNCPEN_API_KEY": "<YOUR_SYNCPEN_API_KEY>"
}
}
}
}
}McpServers
{
"syncpen": {
"command": "npx",
"args": [
"-y",
"syncpen-mcp"
],
"env": {
"SYNCPEN_API_KEY": "<YOUR_SYNCPEN_API_KEY>"
}
}
}Connect Claude Code (or any MCP client) to yourSyncpenworkspace — the writing workspace your AI can actually write in. Your agent can search, read, draft, suggest, comment, organize, and publish in the same live documents you edit.
Don't have an account yet?Create one free atsyncpen.io.
- Build a knowledge base your AI maintains— capture notes, docs, and clips, then let your agent organize, cross-link, and keep it current.
- Write long-form where you publish— articles, docs, whole books; your agent drafts, you approve, and one call ships it to WordPress, Ghost, or Sanity.
- Your agents and you on one project— everyone works in the same live documents; every edit is shared, legible, and attributed.
- Edits with a paper trail— agents propose changes as signed suggestions you accept or reject. Nothing changes silently.
- Research → draft → ship without leaving your tools— clip sources, let your AI draft from them, publish.
- Go toSettings → API Keysin your Syncpen account
- Enable API Access
- Create a new API key
- Copy the key (you'll only see it once!)
Add to your MCP configuration file (~/.mcp.jsonor project-level.mcp.json):
{ "mcpServers": { "syncpen": { "command": "npx", "args": ["-y", "syncpen-mcp"], "env": { "SYNCPEN_API_KEY": "sp_your_api_key_here" } } } }
That's it! Claude Code will automatically download and run the MCP server.
- "List my Syncpen folders"
- "Search for documents that mention authentication"
- "Read my document titled 'API Design Notes'"
- "What documents do I have in my 'Projects' folder?"
- "Publish my 'Launch Post' document to Ghost as a draft"
- "What's changed in my workspace since yesterday?"
For contributing or running from source:
git clone https://github.com/airbuzz/syncpen-mcp.git cd syncpen-mcp npm install npm run build # or: npm run dev (watch mode)
Point your MCP config at the built entry (node /path/to/syncpen-mcp/dist/index.js). It uses the production API by default; setSYNCPEN_API_URLonly to target a local instance.
Local-first agent memory: a plain-Markdown Obsidian vault is the source of truth, with a rebuildable DuckDB index for hybrid BM25 + vector + graph recall.
Persistent memory and semantic search for AI coding assistants across sessions
Give your agent a memory: shared, cited, tenant-isolated knowledge-graph memory for any MCP host. Grounded answers from a local-first June endpoint — abstains rather than guesses.
Decentralized persistent memory for AI agents — encrypted vault storage built on Walrus and Sui.
Persistent memory for AI assistants and coding agents across ChatGPT, Claude, Cursor, and other MCP-compatible tools.
Your portable AI memory vault — memories, skills & configs, shared across every AI tool.
Local Work Model for AI agents that learns from real outcomes.
Adaptive MCP memory system for AI applications. Learns which retrieval strategies work for your data, scores results using cognitive science models, builds a knowledge graph automatically, and validates every parameter change against real query history before adopting it. Patent pending.
Auditable, self-improving knowledge & memory for AI agents over MCP — citation-enforced answers and a replayable why-trace, self-hosted on Postgres.
Turns your task manager into agent memory: hybrid (RRF) retrieval over TickTick or an Obsidian vault via an adapter contract. MCP server + CLI, no vector DB to maintain.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
