---
title: "Graphiti MCP Server: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/mcp-servers/graphiti/
description: "Keeps agent memory as a temporal knowledge graph in FalkorDB or Neo4j, using an LLM to extract entities and facts from each added episode."
---

# Graphiti MCP Server: review, setup & limitations · Undominated.ai

> Keeps agent memory as a temporal knowledge graph in FalkorDB or Neo4j, using an LLM to extract entities and facts from each added episode.

[← Explore all mcp servers](/mcp-servers/)

AGENT MEMORY / Zep

# Graphiti MCP Server

Keeps agent memory as a temporal knowledge graph in FalkorDB or Neo4j, using an LLM to extract entities and facts from each added episode.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/getzep/graphiti/tree/9d56c190926b382a54c5ea03e7680af1d05e1c9d/mcp_server)

SOURCE REVIEW

 Reviewed 2026-10-13
 Evidence 3 linked sources
 Publisher Zep
 Licence [Apache-2.0 ↗](https://github.com/getzep/graphiti/blob/9d56c190926b382a54c5ea03e7680af1d05e1c9d/LICENSE)
 Revision 9d56c190926b
 [Read what was—and wasn’t—checked ↓](#review)

“This is an experimental Model Context Protocol (MCP) server implementation for Graphiti.”

 [Zep · upstream description ↗](https://github.com/getzep/graphiti/blob/9d56c190926b382a54c5ea03e7680af1d05e1c9d/mcp_server/README.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Published in Zep's getzep/graphiti repository under mcp_server/; the README at this commit lists thirteen tools, including add_memory, search_memory_facts, get_episode_entities, delete_episode and clear_graph.
- The README names the supported LLM providers (OpenAI, Anthropic, Gemini, Groq, Azure OpenAI) and embedders (OpenAI, Voyage, Sentence Transformers, Gemini), so extraction can run on the provider the user chooses.

### A good fit for

 - Persistent, queryable memory for an agent, held in a graph database you run
- Tracing which entities and facts an added episode produced, with get_episode_entities, before deleting or correcting it

### Weigh up before choosing

 - The README calls this an experimental implementation. Each added episode is processed by the configured LLM, so memory writes consume model tokens; the README documents tuning for provider 429 rate limits.
- The README says Graphiti core sends anonymous telemetry unless GRAPHITI_TELEMETRY_ENABLED=false.
- clear_graph deletes all data for the given groups. The server was not started.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - mcp_server/README.md at 9d56c190926b382a54c5ea03e7680af1d05e1c9d
- mcp_server/pyproject.toml at the same commit
- LICENSE at the same commit (the README says the server uses the parent project's licence)

### Our findings

 - The README's defaults are HTTP transport at http://localhost:8000/mcp/, FalkorDB in a combined container with the server, OpenAI model gpt-5.5 and text-embedding-3-small.
- On FalkorDB each group_id is stored in its own graph; tools called without group_id use the configured default group.
- mcp_server/pyproject.toml names mcp-server 1.1.0, Python >=3.10,<4, with optional provider extras.

### Not established by this review

 - docker compose up
- Any LLM or embedding call
- Any graph read or write

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Connect a server deliberately.

[Upstream setup instructions ↗](https://github.com/getzep/graphiti/blob/9d56c190926b382a54c5ea03e7680af1d05e1c9d/mcp_server/README.md)

DOCUMENTED COMMAND

 docker compose up Copy command ↗

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

 - Clone getzep/graphiti, copy .env.example to .env in graphiti/mcp_server and set at least one LLM provider key there; the README requires the .env file in that directory. Do not commit keys.
- Run the command above from graphiti/mcp_server; the README says it starts FalkorDB and the MCP server in one container. Point the client at http://localhost:8000/mcp/. It was not run.

### Before you start

 - Docker and Docker Compose
- An OpenAI API key or another supported LLM provider key

### Documented configuration example

Use the client and authentication context described in the setup guidance. Configuration formats vary between hosts.

 {
 "mcpServers": {
 "graphiti-memory": {
 "transport": "http",
 "url": "http://localhost:8000/mcp/"
 }
 }
} Copy configuration ↗

### Compatibility

VS Code · GitHub Copilot · Cursor · Claude Desktop

### Implementation

Python

### Transports

HTTP · stdio

### Local container with LLM-provider credentials

 - Reads and writes the configured FalkorDB or Neo4j graph
- Sends episode content to the configured LLM and embedding providers for extraction

### Cost model

Apache-2.0 source. LLM and embedding calls are billed by the chosen providers; no rate was reviewed.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Graphiti MCP server README ↗](https://github.com/getzep/graphiti/blob/9d56c190926b382a54c5ea03e7680af1d05e1c9d/mcp_server/README.md) Checked 2026-10-13 https://github.com/getzep/graphiti/blob/9d56c190926b382a54c5ea03e7680af1d05e1c9d/mcp_server/README.md Supports: Experimental status, Tools, Defaults and providers, Telemetry, Client configuration
- [Graphiti LICENSE ↗](https://github.com/getzep/graphiti/blob/9d56c190926b382a54c5ea03e7680af1d05e1c9d/LICENSE) Checked 2026-10-13 https://github.com/getzep/graphiti/blob/9d56c190926b382a54c5ea03e7680af1d05e1c9d/LICENSE Supports: Apache License 2.0
- [Graphiti MCP server pyproject.toml ↗](https://github.com/getzep/graphiti/blob/9d56c190926b382a54c5ea03e7680af1d05e1c9d/mcp_server/pyproject.toml) Checked 2026-10-13 https://github.com/getzep/graphiti/blob/9d56c190926b382a54c5ea03e7680af1d05e1c9d/mcp_server/pyproject.toml Supports: Package mcp-server 1.1.0, Provider extras

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Knowledge Graph Memory reference server ↗ Persist named entities, observations and relations in a local JSONL graph between client sessions.](/mcp-servers/memory/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Inspect resource evidence](/tools/)
- [Choose a host](/agents/)
- [Inspect reusable workflows](/skills/)
- [Use Undominated data](/api/)
