klypix-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@klypix-mcpsummarize the canvas roadmap"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
klypix-mcp
An open, local-first, agent-neutral canvas file your AI reads and writes over MCP — works with Claude, Cursor, Cline, any model.
Your AI forgets everything between sessions, and you can't hand it your whole
messy project at once. klypix-mcp fixes that with a single portable file:
.klypixis one file that holds your whole project spatially — text, PDFs, screenshots, audio, code, links — arranged and connected on an infinite canvas.This package is an MCP server: any MCP-capable agent (Claude Desktop, Cursor, Cline, …) can list, read, search, create, and append to your
.klypixcanvases — so your agent gets durable, multimodal, spatial memory.Local-first + agent-neutral. The file lives on your disk. No lab is in the loop — read it with Claude today, GPT tomorrow, a local model next week. No vendor can take it away.
The shared memory layer for your multi-agent stack. A2A moves the messages between agents; MCP connects an agent to its tools;
.klypixis the owned, multimodal context both layers read and write. KLYPIX ships two faces over one engine — an MCP server (klypix-mcp) and an A2A agent (klypix-a2a) — so whichever protocol your stack speaks, the memory node is the same portable file you own. See A2A.md.
Quick start (60 seconds)
# point it at any folder of .klypix files (a "vault")
npx klypix-mcp --vault ./canvasesThen add it to your MCP client. For Claude Desktop, in
claude_desktop_config.json:
{
"mcpServers": {
"klypix": {
"command": "npx",
"args": ["-y", "klypix-mcp", "--vault", "/absolute/path/to/canvases"]
}
}
}Now ask your agent things like "summarize the canvas roadmap," "turn these
notes into a board," or "add a card with the decision we just made."
Related MCP server: FilDOS MCP Server
Tools the server exposes
Tool | What it does |
| List every |
| Read a canvas as markdown (cards, the connection graph, |
| Search across canvases by name + content |
| Cross-project memory search across every registered brain |
| Hubs, orphaned decisions, stale questions, area sizes |
| Find + draw related-but-unlinked cards (densify the graph) |
| Flag committed-but-unrecorded DB migrations (the brain can't see prod) |
| Create a new |
| Append cards/connections to an existing canvas (positions preserved) |
Tools vs. the automatic brain
This package is the agent-neutral read/write surface — any MCP client (Claude Code, Claude Desktop, Cursor, Cline, Windsurf…) gets the tools above and can read, search, and write canvases on demand (pull). That works in any agent, in any project.
The automatic brain — auto-capturing decisions from your work, injecting the
relevant cards into each prompt, and coordinating across concurrent sessions
(push) — runs in a host hook, which is a Claude Code / KLYPIX-desktop
feature, not part of this npm package. So npx klypix-mcp gives you the tools
everywhere; the hands-free brain comes with the KLYPIX desktop app
or the Claude Code project-brain hook. (search_all_brains is also hook-fed — it
reads the cross-project registry the hook writes, so it stays empty until a hook
has registered at least one brain.)
Also speaks A2A (Agent-to-Agent)
The same engine is exposed as an A2A agent so other agents and orchestrators can delegate memory tasks to KLYPIX as a discoverable peer:
npx -p klypix-mcp klypix-a2a --vault ./canvases # 127.0.0.1:41241
# Agent Card: http://127.0.0.1:41241/.well-known/agent-card.jsonSkills: make_board, remember, recall, read_canvas, list_canvases,
brain_insights, search_all_brains. Unlike a typical A2A agent that returns
text, KLYPIX returns the .klypix board itself as a multimodal artifact.
Full protocol details (JSON-RPC methods, message shapes, streaming) in
A2A.md.
Use it as a library
import { parseKlypix, buildKlypix, appendToKlypix, structToMarkdown } from 'klypix-mcp';…or read/write from the shell:
npx -p klypix-mcp klypix-read path/to/board.klypix # → markdown brief
echo '{ "title": "Plan", "cards": [{ "text": "kickoff" }] }' \
| npx -p klypix-mcp klypix-write --out plan.klypixThe .klypix format
A .klypix is just a ZIP of JSON + assets — open, inspectable, versioned.
Full spec in FORMAT.md. The point: you own the file, and any agent
can drive it.
Why this exists
Frontier labs are racing to put your context inside their canvas — a roach
motel your work checks into and never leaves for a competitor. klypix-mcp is
the opposite: your project, your file, any model, offline. That's the one
thing a lab is structurally disincentivized to build.
MIT licensed. Built by Dahshan Labs. The KLYPIX desktop app is the spatial editor for these files — but the file and this server are fully open and work without it.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/dahshanlabs/klypix-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server