Cairn logo

Cairn

Organizes a local workspace through MCP tools for file operations, tagging, document import, and search.

Install Cairn

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "cairn-4": {
      "command": "uvx",
      "args": [
        "cairn-mcp-server"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 48 tools correctly (7d ago).

Overview

Cairn MCP server gives an MCP-compatible agent local tools for listing, reading, searching, editing, moving, tagging, importing, and retrieving files. It runs against a configured workspace directory, stores tags in portable `.uni` documents, and keeps filesystem data and optional indexes local. Read-only operations can run freely, while edits, moves, and deletes are annotated as destructive for client approval. Reach for it when an agent needs to organize notes or documents without an account, cloud service, or separate database.

Use cases

  • Organize a notes folder with agent-assisted file operations
  • Tag documents in a local workspace
  • Search and retrieve related notes
  • Import office documents into editable local files
  • Review file changes through client approval prompts

Key features

  • 26 MCP tools for local file organization
  • Read, search, grep, edit, move, and delete files
  • Tag and retrieve `.uni` documents
  • Import DOCX, PDF, PPTX, XLSX, and Markdown
  • Optional local embeddings-based retrieval
  • MCP annotations for read-only and destructive actions

Tools48

What Cairn lets your agent do. Expand a tool for its parameters.

Verified live~6.4k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

5/5 checks healthy over the last 35d

What it can do

From the 48 tools this server returned when we ran it; 48 declare their own safety hints.

Can delete or modify data · 5Writes files · 3Handles credentials · 2Read-only tools · 40
Network at startup2 connections
Files written at startup30

Observed 2026-10-16 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 14d ago via OSV.dev · cairn-mcp-server (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars2Stargazers on the source repository.
Last commit2mo agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed48Callable tools this server registers over MCP.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Cairn works

What Cairn MCP server does

Cairn MCP server connects an MCP client to a folder on the local filesystem and exposes a file-organization toolset. Its documented capabilities include listing and reading files, text search, grep, editing, moving, tagging, deleting, importing documents, and semantic retrieval. The package is intended to supply tools rather than an agent loop; Claude Code, Codex, Cursor, or another MCP client handles the conversation and approvals.

A workspace is an ordinary directory. Cairn can work with its .uni document format, where each document is represented as JSON containing a UUID, HTML content, metadata, and tags. Tags are stored inside the file, and the filesystem remains the source of truth. Imported source documents are kept by default while Cairn creates editable .uni documents from supported formats.

How it works

The MCP server is a thin adapter over Cairn’s local core. It exposes 26 tools, along with MCP resources and prompts, and marks operations according to their risk. Listing, reading, searching, grepping, and retrieving are read-only operations. Moving, deleting, or editing files are destructive operations, allowing compatible clients to request confirmation before making changes.

The default retrieval method is lexical and requires no model or API key. Embeddings-based retrieval is optional. When enabled, it can use an OpenAI-compatible endpoint, including local services such as Ollama or LM Studio. Vectors are stored in a SQLite index under <workspace>/.cairn/, so the index remains on the machine.

This makes the Cairn MCP server suitable for organizing a notes directory, applying tags across documents, locating related content, or importing a collection for agent-assisted cleanup. Because the tool can rename, move, edit, and delete files, testing against a copy of important material is appropriate.

Setup and configuration

The server can be launched with uvx, which requires uv. A Claude Code configuration uses the form:

Terminal
claude mcp add cairn -- uvx cairn-mcp-server --workspace ~/Documents/notes

Codex uses the equivalent codex mcp add command. Other MCP clients can use a JSON server entry with uvx as the command, cairn-mcp-server as the package argument, and --workspace followed by the target directory. Cairn expands ~ in both command-line and configuration paths.

The workspace is supplied as a command-line option rather than an environment variable. A separate cairn-cli package is available for direct commands, including tree inspection and retrieval, but it is not required for MCP use.

Limitations and notes

Embeddings are not enabled by default and require a compatible endpoint when used. The project is described as young, with richer document round-tripping, saved views, additional retrieval backends, and broader client recipes listed as future work.

The optional web interface is separate from the MCP server and runs locally through cairn-cli serve; it is not required for agent access. The project is licensed under MIT.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Cairn

Cairn is an MCP server that connects AI clients to a local workspace folder and provides tools to list, read, search, grep, edit, move, delete, tag, import, and retrieve documents. It runs locally, uses the filesystem as its source of truth, and does not require an account or cloud service.

Install `uv`, then add Cairn with `uvx`, such as `claude mcp add cairn -- uvx cairn-mcp-server --workspace ~/Documents/notes`. Codex has an equivalent command, while other MCP clients can use a JSON configuration with the same package and workspace arguments.

Yes, Cairn works with Cursor through its MCP JSON configuration. Set `uvx` as the command, pass `cairn-mcp-server` and `--workspace` in the arguments, and point the workspace at the folder the agent should organize.

No, the default lexical retriever requires no API key. Embeddings-based retrieval is optional and can use an OpenAI-compatible endpoint, including local services such as Ollama or LM Studio.

Yes, Cairn provides editing and moving tools, along with deletion. These actions are marked as destructive so compatible MCP clients can ask for confirmation before applying them.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewCairn AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/cairn-4?style=directory)](https://allmcps.com/mcp/cairn-4)
HTML Embed
<a href="https://allmcps.com/mcp/cairn-4"><img src="https://allmcps.com/api/badge/cairn-4?style=directory" alt="Cairn on AllMCPs" /></a>