mcpField
W
wisdomgraph

wisdomgraph

Local
github.com/cklam12345Memory & Knowledge2Updated 16w ago
Repository

About wisdomgraph

wisdomgraph is an npm shim for a Python package that gives Claude Code accumulative, persistent memory backed by Neo4j. Its five MCP tools ingest content, store facts, query the graph, promote knowledge, and report graph summaries.

Key features

  1. 01Persistent Neo4j-backed memory
  2. 02Ingest files, directories, and URLs
  3. 03Store facts and insights explicitly
  4. 04Query the graph with read-only Cypher
  5. 05Promote knowledge through DIKW tiers

Use cases

  1. 01Retain useful knowledge across Claude Code sessions
  2. 02Ingest reference files or URLs into memory
  3. 03Record decisions and query connected facts

MCP support

The Python package exposes five MCP tools for ingesting, remembering, querying, reflecting on, and reporting graph memory. The npm package acts as a shim for starting it.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "cklam12345-wisdomgraph": {
      "command": "npx",
      "args": [
        "-y",
        "wisdomgraph"
      ],
      "env": {
        "WISDOM_NEO4J_PASSWORD": "<WISDOM_NEO4J_PASSWORD>"
      }
    }
  }
}
Run commandnpx -y wisdomgraph
Environment variables to set
WISDOM_NEO4J_PASSWORDSecretNeo4j password for wisdomGraph. Set via `wisdom connect` or export directly.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmwisdomgraph0.2.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

wisdomGraph

Accumulative Neo4j-native DIKW memory for Claude Code — permanent knowledge across sessions.

PyPI npm License: MIT

This is the npm shim for wisdomGraph. All logic lives in the Python package.

Quick start

# 1. Install Python package
pip install 'wisdomgraph[mcp]'

# 2. Start Neo4j (local DozerDB)
wisdom docker up
wisdom connect bolt://localhost:7687 --user neo4j --password password

# 3. Register MCP server in Claude Code
wisdom mcp-install

MCP config (via npx)

{
  "mcpServers": {
    "wisdomGraph": {
      "command": "npx",
      "args": ["wisdomgraph"]
    }
  }
}

What it does

wisdomGraph gives Claude Code permanent, accumulative memory backed by Neo4j.

Five MCP tools:

  • wisdom_ingest — absorb files, directories, or URLs
  • wisdom_remember — store facts, decisions, insights explicitly
  • wisdom_query — read-only Cypher traversal
  • wisdom_reflect — DIKW promotion pipeline
  • wisdom_report — tier counts + top Wisdom nodes

The graph never resets. Every session compounds.

Links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.