How to add Graphiti MCP to Claude Desktop

Temporal knowledge-graph memory for agents: add episodes and search facts over FalkorDB or Neo4j, from Zep. Paste the config into ~/Library/Application Support/Claude/claude_desktop_config.json and restart Claude Desktop.

Last updated June 14, 2026 · 28k★ · http · apikey · official

Claude Desktop config for Graphiti MCP

git clone https://github.com/getzep/graphiti.git && cd graphiti/mcp_server && docker compose up

{
  "mcpServers": {
    "graphiti-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "http://localhost:8000/mcp/"
      ]
    }
  }
}

Claude Desktop connects to remote servers through the `mcp-remote` proxy (installed on first run via npx). Restart Claude Desktop after saving.

Setup steps

1Open Claude Desktop → Settings → Developer → Edit Config (this opens ~/Library/Application Support/Claude/claude_desktop_config.json).
2Paste the Graphiti MCP config below under the top-level "mcpServers" key.
3Fill in any placeholder secrets (API keys, paths) in the snippet.
4Save the file, then fully quit and reopen Claude Desktop.
5Open a chat and confirm Graphiti MCP's tools appear under the 🔌 tools menu.

Before you start

Docker and Docker Compose (default FalkorDB combined container)
An LLM provider API key — OPENAI_API_KEY by default; Anthropic, Gemini, Groq, and Azure OpenAI are also supported
Python 3.10+ and uv only if running the server standalone against an external database
Neo4j 5.26+ if you choose it over the bundled FalkorDB

What Graphiti MCP can do in Claude Desktop

add_memory

Add an episode (text, JSON, or message format) to the graph; queued for async LLM extraction.

add_triplet

Insert a single source-fact-target triplet directly, bypassing extraction.

search_nodes

Search entity nodes with entity_types and center_node_uuid filters.

search_memory_facts

Search facts (edges) with edge_types, center node, and valid_at/invalid_at date-range filters.

summarize_saga

Generate or refresh the running summary of a saga's episodes.

build_communities

Detect entity communities and produce higher-level community summaries.

get_episode_entities

Trace provenance: which entities and facts specific episodes created.

delete_entity_edge

Delete an entity edge from the graph.

Security

Self-hosted: graph data stays in your FalkorDB/Neo4j instance, but every episode's content is sent to the configured LLM provider (OpenAI by default) for entity extraction. API keys live in a server-side .env file, and anonymous telemetry is on unless you set GRAPHITI_TELEMETRY_ENABLED=false.

Graphiti MCP + Claude Desktop FAQ

Where is the Claude Desktop config file?

Claude Desktop reads MCP servers from ~/Library/Application Support/Claude/claude_desktop_config.json. Paste the Graphiti MCP config there under the "mcpServers" key and restart the client.

Is Graphiti MCP safe to use with Claude Desktop?

Is the Graphiti MCP server free?

Yes — Apache-2.0 and fully self-hosted, with FalkorDB bundled in the default container. Your real cost is LLM usage: each episode triggers multiple extraction/dedup/summarization calls to your configured provider, which is also why the SEMAPHORE_LIMIT concurrency setting matters.

How is this different from a vector-store memory server?

Graphiti builds an entity/relationship graph with bi-temporal validity rather than storing chunks. You get structured facts with valid_at/invalid_at history, date-range queries, community summaries, and provenance tracing — at the price of running a graph database and paying for extraction LLM calls.

Why am I seeing 429 rate-limit errors during ingestion?

Your SEMAPHORE_LIMIT is too high for your LLM tier. The default of 10 assumes roughly OpenAI Tier 3 (500 RPM); the README suggests 1-2 for free tiers and up to 20-50 for Tier 4. Each episode fans out into several concurrent LLM requests, so lower it until 429s stop.

View repo Full Graphiti MCP page