# Graphiti MCP Demo

> Use this tool when you need to build and persist dynamic knowledge graphs in real-time, solving problems of contextual understanding and information retrieval. It takes in data inputs and outputs a graph structure, enabling AI agents to store and query complex relationships. Ideal for applications requiring continuous learning and memory retention, such as conversational AI and recommender systems.

Canonical page: https://skillsregistry.net/skills/kartikk-26-graphiti-mcp-demo  
JSON: https://api.skillsregistry.net/v1/skills/kartikk-26-graphiti-mcp-demo

## Description

Enables AI agents to build real-time knowledge graphs using Zep's Graphiti memory, persisting context in Neo4j.

## Trust

- **Trust score (0–1):** 0.78
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/y8ux76sjxk)
- **Repository:** <https://github.com/Kartikk-26/Graphiti-MCP-Demo>

## 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": "kartikk-26-graphiti-mcp-demo"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kartikk-26-graphiti-mcp-demo` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kartikk-26-graphiti-mcp-demo/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