Loom MCP Server

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

Local serverstdioPython

What is the Loom MCP server?

Loom MCP server exists for a simple reason — assistants are far more useful when they can act on Loom directly instead of describing what you should do. Local-first personal knowledge base. Cited answers from your vault via vector + graph retrieval.

What you get

Point it at your notes folder. Loom indexes everything, maps typed relationships between ideas (which notes cite the same sources, which contradict each other, which extend the same argument), and builds a persistent graph that gets smarter as you add more. Your vault, vector index, and graph stay on your machine. Only the specific passages behind an answer go to Claude for synthesis — or skip that and run a local model instead.

  • Ask your notes anything — semantic search + knowledge graph traversal with cited answers. Retrieval runs locally; synthesis uses Claude by default (or a local model)
  • See what you forgot: weekly reports find notes you read months ago that connect to what you're working on now (Knowledge Archaeology, live)
  • Track how your thinking evolved: monthly reports show how your understanding of a topic shifted over time (Temporal Reasoning, live)
  • Know where you're thin: weekly reports rank concepts where your coverage is shallow (Epistemic Audit, live)
  • Ingest everything automatically — drop PDFs, audio, and web URLs into one folder. Loom does the rest
  • Store your vault, index, or graph anywhere but your machine

What the assistant can call

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

  • Gotchas — The Gotchas tool exposed by this server

Configuration and credentials

You will need 2 environment variables: ANTHROPIC_API_KEY, LOOM_VAULT_PATH. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

fastapi on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Plenty of payments and commerce 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. Loom's toolset — Gotchas — is a fair guide to whether it matches your workflow. It is maintained by KlossKarl; 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.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the loom mcp server does with a few real requests.

Available tools

ToolWhat it does
GotchasThe Gotchas tool exposed by this server.

How to install the Loom MCP server

{
  "mcpServers": {
    "loom": {
      "command": "python",
      "args": ["C:\\path\\to\\loom\\loom_mcp.py"]
    }
  }
}

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

Configuration

VariableDescriptionRequired
ANTHROPIC_API_KEYCredential the server authenticates with.Yes
LOOM_VAULT_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Loom to Gotchas.

Frequently asked questions

It connects Loom to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (Gotchas) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Loom directly.