# KnowledgeGraph MCP Server

> Use this tool when you need to enable large language models (LLMs) to retain context and memory across conversations. It solves the problem of knowledge retention and recall by storing entities, relationships, and observations in a knowledge graph, supporting PostgreSQL or SQLite backends. This tool is ideal for use cases requiring persistent memory and contextual understanding, with input/output capabilities for integrating with LLMs and database systems.

Canonical page: https://skillsregistry.net/skills/n-r-w-knowledgegraph-mcp  
JSON: https://api.skillsregistry.net/v1/skills/n-r-w-knowledgegraph-mcp

## Description

Provides LLMs with persistent memory across conversations using a knowledge graph that stores entities, relationships, and observations with support for PostgreSQL or SQLite backends.

## Trust

- **Trust score (0–1):** 0.82
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/o19h4z5us7)
- **Repository:** <https://github.com/n-r-w/knowledgegraph-mcp>

## 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": "n-r-w-knowledgegraph-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/n-r-w-knowledgegraph-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/n-r-w-knowledgegraph-mcp/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