# Graphiti MCP Server

> Use this tool when you need to extract and store complex relationships from unstructured text data, solving problems like entity disambiguation and knowledge graph construction. It takes in text inputs and outputs a Neo4j database with extracted entities and relationships, supporting multiple isolated projects. Ideal for use cases requiring scalable and organized knowledge graph management, such as data integration and semantic search applications.

Canonical page: https://skillsregistry.net/skills/rawr-ai-mcp-graphiti  
JSON: https://api.skillsregistry.net/v1/skills/rawr-ai-mcp-graphiti

## Description

This MCP server extracts entities and relationships from text and stores them in Neo4j, supporting multiple isolated knowledge graph projects that share the same database.

## Trust

- **Trust score (0–1):** 0.72
- **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:** [Glama](https://glama.ai/mcp/servers/kmjnigvk15)
- **Repository:** <https://github.com/rawr-ai/mcp-graphiti>

## 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": "rawr-ai-mcp-graphiti"
    }
  }
}
```

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