Fuzzy Memory MCP Server

MCP server for enabling memory for Claude through a knowledge graph

Local serverstdio

What is the Fuzzy Memory MCP MCP server?

Most knowledge and memory work still happens through a UI a human drives. Fuzzy Memory MCP MCP server moves it into the conversation instead. MCP server for enabling memory for Claude through a knowledge graph.

The short version

A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats. This version has been enhanced with fuse.js to provide fuzzy, semantic searching capabilities.

Getting it running

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

The tools it exposes

The server publishes 14 tools. What each one is for:

  • create_entities — Create multiple new entities in the knowledge graph
  • Input — entities (array of objects)
  • create_relations — Create multiple new relations between entities
  • add_observations — Add new observations to existing entities
  • delete_entities — Remove entities and their relations
  • delete_observations — Remove specific observations from entities
  • delete_relations — Remove specific relations from the graph
  • read_graph — Read the entire knowledge graph
  • search_nodes — Performs a fuzzy semantic search for nodes in the knowledge graph using Fuse.js
  • entity — The matched entity object
  • score — Confidence score from 0.0 to 1.0 (higher is better)
  • Threshold — 0.6 (0.0 = perfect match, 1.0 = matches anything)

What it needs from you

Configuration is passed through the environment: MEMORY_FILE_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Node.js and npm - Docker (for building the Docker image)

Things to watch

  • 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 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Fuzzy Memory MCP.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Plenty of knowledge and memory 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. Fuzzy Memory MCP's toolset — create_entities, Input, create_relations and 11 more — is a fair guide to whether it matches your workflow. It is maintained by flrngel; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
create_entitiesCreate multiple new entities in the knowledge graph
Inputentities (array of objects)
create_relationsCreate multiple new relations between entities
add_observationsAdd new observations to existing entities
delete_entitiesRemove entities and their relations
delete_observationsRemove specific observations from entities
delete_relationsRemove specific relations from the graph
read_graphRead the entire knowledge graph
search_nodesPerforms a fuzzy semantic search for nodes in the knowledge graph using Fuse.js
entityThe matched entity object
scoreConfidence score from 0.0 to 1.0 (higher is better)
Threshold0.6 (0.0 = perfect match, 1.0 = matches anything)
Locationindependent matching
open_nodesRetrieve specific nodes by name

How to install the Fuzzy Memory MCP MCP server

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "github:flrngel/fuzzy-memory-mcp#main"
      ]
    }
  }
}

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

Configuration

  • Node.js and npm - Docker (for building the Docker image)
VariableDescriptionRequired
MEMORY_FILE_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Fuzzy Memory MCP to create entities.
  • Use Fuzzy Memory MCP to Input.
  • Use Fuzzy Memory MCP to create relations.

Frequently asked questions

It connects Fuzzy Memory MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (create_entities, Input, create_relations, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Fuzzy Memory MCP directly.