Cairn runs on your own machine — the client starts it, so there is no endpoint to ping. 81 installs a week from pypi. Last commit 29 Jul 2026.
Local-first file-organization tools for your AI agent: tag, query, and digest a folder. No cloud.
We read the source, 22 h ago · rules 3dff92dd89df
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
for p in root.rglob("*.md"):
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
return __import__(module)
for p in root.rglob("*.md"):
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Cairn and you get told the day something new turns up.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add cairn -- uvx cairn-mcp-server
{
"mcpServers": {
"cairn": {
"args": [
"cairn-mcp-server"
],
"command": "uvx"
}
}
}
[mcp_servers.cairn]
command = "uvx"
args = ["cairn-mcp-server"]
{
"mcpServers": {
"cairn": {
"args": [
"cairn-mcp-server"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"cairn": {
"args": [
"cairn-mcp-server"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
CAIRN_WORKSPACE (Path to the folder Cairn operates on. If unset, defaults to the current working directory. You can also pass --workspace on the command line instead.).
The author declared them in the registry entry; get the values from the project itself.
Local memory for AI agents. One SQLite file on your machine — no cloud, no account.
Local-first memory and session continuity for AI coding agents over MCP. No cloud, no telemetry.
Persistent memory, coordination, and learning for AI agents. Local-first, 25 MCP tools.
Video as a queryable local asset for AI agents — 47 tools for YouTube, social, and local media.
Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.
Query your local super-log bench from an AI agent - read-only log tools over the hub.
Let AI agents draw on your local-first KaiBoard whiteboards (relay or local folder).
Query and troubleshoot your local network in plain language: 37 tools, strictly local, no cloud.
Answers built from our own checks of this server.