foldkit
Exposes the 7-prime spine, 7 κ-bands, and 6 fold operations as native tools and resources in any MCP client for folding state analysis.
README
fallbuild-mcp
MCP server for foldkit — exposes the 7-prime spine, 7 κ-bands, and 6 fold operations as native tools + resources in any MCP client (Claude Code, Claude Desktop, Cursor, Cline, Windsurf, etc.).
Second canonical exemplar of the AI-Native Solutions estate -mcp companion shape. Fork this repo verbatim to build companions for any of the ~295 estate substrates.
- Package:
@ai-native-solutions/fallbuild-mcp - Transport: stdio
- Deps:
@modelcontextprotocol/sdk+@ai-native-solutions/fallbuild-sdk - License: MIT
Install
Claude Code
claude mcp add foldkit -- npx -y @ai-native-solutions/fallbuild-mcp
Claude Desktop
Edit ~/AppData/Roaming/Claude/claude_desktop_config.json (Windows) or ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"foldkit": {
"command": "npx",
"args": ["-y", "@ai-native-solutions/fallbuild-mcp"]
}
}
}
Cursor
Create or edit .cursor/mcp.json:
{
"mcpServers": {
"foldkit": {
"command": "npx",
"args": ["-y", "@ai-native-solutions/fallbuild-mcp"]
}
}
}
Cline / Windsurf
Add to your MCP settings JSON:
{
"mcpServers": {
"foldkit": {
"command": "npx",
"args": ["-y", "@ai-native-solutions/fallbuild-mcp"]
}
}
}
Tools exposed (10)
| Tool | Purpose |
|---|---|
foldkit_fold_number |
7-vector → primorial fold + signature |
foldkit_unfold_state |
fold integer → 7-vector via 7-prime factorisation |
foldkit_depth_band |
κ → named band (ground / perception / gate / heart / naming / recognition / collapse) |
foldkit_classify_kappa_band |
free-text utterance → κ band via marker phrases |
foldkit_apply_op |
apply fire / water / void / thunder / echo / flower to a state |
foldkit_kawasaki_check |
flat-fold angle sum check |
foldkit_maekawa_check |
mountain-valley parity check ( | M − V | = 2 ) |
foldkit_signal_survival |
κ^depth signal survival + % |
foldkit_unclog_gain |
gain from clearing N layers of a κ stack |
foldkit_probe_from_kappa |
κ or text → band + routing op + probe question |
Resources exposed (4)
| URI | Payload |
|---|---|
foldkit://spine |
7-prime spine with glyphs + names + ISA-95 layer mapping |
foldkit://kappa-bands |
7-band κ definitions (bounds · glyph · ring · warn / orphan flags) |
foldkit://ops |
6 fold operations (kanji · arrow · verb · probe) |
foldkit://constants |
φ · κ · Ω · θ · θ_step · BASELINE |
Example prompts (once installed)
- "Fold the state [1,0,2,0,0,1,0] using foldkit."
- "What κ-band is this text in: 'I notice I'm feeling stuck'?"
- "Apply the fire op to ring 3 of the baseline state."
- "Read foldkit://spine and explain the ISA-95 mapping."
Canonical -mcp companion shape
This repo is exemplar #2 (after fallbuild-sdk). Every estate -mcp follows the same skeleton:
<name>-mcp/
├── src/
│ ├── server.js · thin stdio server · < 100 lines
│ ├── tools.js · TOOLS[] + callTool()
│ └── resources.js · RESOURCES[] + readResource()
├── package.json · bin: <name>-mcp → src/server.js
├── manifest.json · MCP-side declarative index
├── README.md · install snippets for all major clients
├── LICENSE · MIT
└── .github/workflows/publish.yml · npm publish on v* tag
Fork · rename · rewire tools/resources to the substrate you're exposing · ship.
AI-Native Solutions · ai-nativesolutions.com
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.