Loom MCP Server

by klosskarl Your server? Claim it

local only

Loom runs on your own machine — the client starts it, so there is no endpoint to ping. 34 installs a week from pypi.

Local-first personal knowledge base. Cited answers from your vault via vector + graph retrieval.

The linked repository no longer exists on GitHub — it was deleted or made private.

Installs per day peak 22 · avg 8 · -50% w/w

a month agotoday

Installs / week

pypi · loom-pkm

—

Stars

on GitHub

—

Last commit

from GitHub

—

License

language unknown

This one has been quiet for a while

Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.

Connect this server

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 Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add loom -- uvx loom-pkm

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "loom": {
      "command": "uvx",
      "args": [
        "loom-pkm"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.loom]
command = "uvx"
args = ["loom-pkm"]

.cursor/mcp.json

{
  "mcpServers": {
    "loom": {
      "command": "uvx",
      "args": [
        "loom-pkm"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "loom": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "loom-pkm"
      ]
    }
  }
}

Alternatives to Loom

same job, measured the same way

MiniRAG

by kimelody

Lightweight self-hosted RAG knowledge base with hybrid retrieval and cited answers.

answering

Semurg agent memory

by semurg

Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.

1 207 installs/wk local only

Local Memory

by studiomeyer-io

Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.

111 installs/wk local only

TubExperto

by jupediaz

Personal YouTube AI knowledge base powered by RAG. Query your subscribed YouTube channels.

answering

Calypso Multimodal RAG MCP

by calypso-so

Calypso multimodal RAG for grounded answers from docs, images, charts, and knowledge.

121 installs/wk local only

RAG MCP

by jaimenbell

Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.

106 installs/wk local only

Contexta

by contexta

Persistent memory and knowledge graph for AI assistants — keyword + vector + graph search.

answering

loci

by ivenkoolab

Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.

480 installs/wk local only

Loom — questions

Answers built from our own checks of this server.

Why is there no uptime for Loom?

Loom runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package loom-pkm was installed 34 times last week.

Is Loom still maintained?

The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.

How do I connect Loom?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls loom-pkm straight from pypi; nothing to host, nothing to sign up for.

How many people use Loom?

The pypi package loom-pkm was installed 34 times in the last week. Week over week that is -50%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.