# Graphiti MCP Server

> Use this tool when you need to manage complex knowledge graphs and enable semantic search for AI agents. It solves problems related to dynamic graph management, entity disambiguation, and contextual understanding, providing inputs such as graph queries and outputs like relevant node relationships. Ideal for use cases requiring integrated knowledge representation and retrieval, such as question answering, entity recognition, and recommendation systems.

Canonical page: https://skillsregistry.net/skills/gifflet-graphiti-mcp-server  
JSON: https://api.skillsregistry.net/v1/skills/gifflet-graphiti-mcp-server

## Description

A knowledge graph server for AI agents, built with Neo4j and integrated with Model Context Protocol, enabling dynamic graph management and semantic search.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/amejrysdct)
- **Repository:** <https://github.com/gifflet/graphiti-mcp-server>

## 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": "gifflet-graphiti-mcp-server"
    }
  }
}
```

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