# Knowledge Graph

> Use this tool when you need to enhance AI personalization and context retention in applications like chatbots or virtual assistants. It provides a local graph database for creating, querying, and manipulating entities and relationships, allowing assistants to build and maintain structured knowledge across conversations. The Knowledge Graph tool accepts user and context data as inputs and outputs personalized responses, making it ideal for use cases requiring long-term information persistence and retrieval in natural language interactions.

Canonical page: https://skillsregistry.net/skills/shaneholloman-knowledge-graph  
JSON: https://api.skillsregistry.net/v1/skills/shaneholloman-knowledge-graph

## Description

This knowledge graph MCP server, developed by Anthropic, enables persistent memory for AI assistants through a local graph database. It provides tools for creating, querying, and manipulating entities and relationships, allowing assistants to build and maintain structured knowledge about users and contexts across conversations. The implementation uses TypeScript and file-based storage, with a customizable memory path for flexibility. It's designed for enhancing AI personalization and context retention in applications like chatbots, virtual assistants, or any scenario requiring long-term information persistence and retrieval in natural language interactions.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/shaneholloman-knowledge-graph)
- **Repository:** <https://github.com/shaneholloman/mcp-knowledge-graph>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "shaneholloman-knowledge-graph"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/shaneholloman-knowledge-graph` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/shaneholloman-knowledge-graph/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt