# Graphiti

**Type:** Official

**Source Type:** Repository

**Source:** [GitHub](https://github.com/getzep/graphiti/blob/main/mcp_server/README.md)

**Description:** Graphiti MCP server enables AI assistants to interact with graph-based data structures and knowledge graphs. It provides capabilities for graph querying, relationship mapping, and knowledge graph operations for complex data relationship analysis.

**Configuration Parameters:**

* **Neo4j connection URI** \* - Configuration value. Default: `example.com`
* **Neo4j username** \* - Username for authentication. Default: `neo4j`
* **Neo4j password** \* - Password for authentication. Default: `password`
* **OpenAI API key** \* - API key for authentication. Default: `sk-XXXXXXXX`
* **Model name for OpenAI** \* - Configuration value. Default: `gpt-4.1-mini`

**Setup Steps:**

1. Log in to your Graphiti account
2. Navigate to Settings → API Settings → API Keys
3. Generate a new API token or key
4. Copy the token for configuration
5. Ensure your account has appropriate permissions for Graphiti API access

***


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.natoma.ai/apps/graphiti.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.