Iwe MCP Server

IWE turns a directory of markdown files into a knowledge graph — a connected structure you browse from your editor and your AI queries from the

Local serverstdioGo

What is the Iwe MCP server?

Iwe MCP server exists for a simple reason — assistants are far more useful when they can act on Iwe directly instead of describing what you should do. IWE turns a directory of markdown files into a knowledge graph — a connected structure you browse from your editor and your AI queries from the command line. Same files, same links, two interfaces. No cloud, no database, no lock-in.

What the assistant can call

Once Iwe is connected, these are the calls the assistant has available:

  • find — Search notes with fuzzy matching
  • retrieve — Get a note with its children and parent context
  • tree — Show the hierarchy from any starting point
  • squash — Flatten a subtree into one document
  • new — Create a note (accepts content from stdin)
  • extract — Pull a section into its own note
  • inline — Merge a linked note back into its parent
  • rename — Rename a note; all links update automatically
  • delete — Remove a note and clean up references

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Choosing this one

Plenty of planning and project tracking servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Iwe's toolset — find, retrieve, tree and 6 more — is a fair guide to whether it matches your workflow. It is maintained by iwe-org; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Iwe.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the iwe mcp server does with a few real requests.

Available tools

ToolWhat it does
findSearch notes with fuzzy matching
retrieveGet a note with its children and parent context
treeShow the hierarchy from any starting point
squashFlatten a subtree into one document
newCreate a note (accepts content from stdin)
extractPull a section into its own note
inlineMerge a linked note back into its parent
renameRename a note; all links update automatically
deleteRemove a note and clean up references

How to install the Iwe MCP server

{
     "mcpServers": {
       "iwe": {
         "command": "iwec",
         "cwd": "~/notes"
       }
     }
   }

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Iwe to find.
  • Use Iwe to retrieve.
  • Use Iwe to tree.

Frequently asked questions

It connects Iwe to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (find, retrieve, tree, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Iwe directly.