iwe
Level AMCP ecosystemNot an MCP ServerLocalMarkdown knowledge graph — LSP for your editor, CLI + MCP memory for your AI agents
Overview
IWE is a shared Markdown knowledge base where you and your AI agents work on the same notes. Notes live as linked Markdown documents in a local folder; agents can read, write, and organize them, and anything an agent saves is an ordinary note you can browse, correct, or delete. It adds link autocomplete, backlinks, and search to editors like Neovim, Helix, VS Code, and Zed, and offers a CLI plus an MCP server usable with Claude Code, Codex, Gemini, Cursor, and other MCP-capable tools.
Installation
MCP client config (paste into mcp.json)
{
"mcpServers": {
"iwe": {
"command": "npx",
"args": [
"-y",
"@iwe-org/mcp"
]
}
}
}Agent install prompt
Copy and paste into Cursor / Claude / other agents to install this MCP for you
Please read this MCP repository and install it into my current environment:
https://github.com/iwe-org/iwe
Known working client config (can write into mcp.json):
{
"mcpServers": {
"iwe": {
"command": "npx",
"args": [
"-y",
"@iwe-org/mcp"
]
}
}
}
Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.
Related servers
mempalaceThe best-benchmarked open-source AI memory system. And it's free.private-gptComplete API layer for private AI applications on local models: RAG, skills, toocodebase-memory-mcpLocal code intelligence for developers and AI agents. Connect code, docs and infcogneeCognee is the open-source AI memory platform for agents. Give your AI agents pergraphitiBuild Real-Time Knowledge Graphs for AI AgentssupermemoryMemory and context engine + app that is extremely fast, scalable, and can be run