Graphiti MCP Server
Officialby gifflet
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NEO4J_URI | No | Neo4j connection URI | bolt://neo4j:7687 |
| MODEL_NAME | No | Main LLM model to use | gpt-4.1-mini |
| NEO4J_USER | No | Neo4j username | neo4j |
| NEO4J_PASSWORD | No | Neo4j password | demodemo |
| OPENAI_API_KEY | No | Your OpenAI API key, required for standard OpenAI | |
| LLM_TEMPERATURE | No | LLM temperature (0.0-2.0) | 0.0 |
| MCP_SERVER_HOST | No | MCP server host binding | |
| OPENAI_BASE_URL | No | Custom OpenAI API endpoint | |
| SEMAPHORE_LIMIT | No | Concurrent operation limit for LLM calls | 10 |
| SMALL_MODEL_NAME | No | Small LLM model for lighter tasks | gpt-4.1-nano |
| EMBEDDER_MODEL_NAME | No | Embedding model | text-embedding-3-small |
| AZURE_OPENAI_ENDPOINT | No | Azure OpenAI endpoint URL | |
| AZURE_OPENAI_API_VERSION | No | Azure OpenAI API version | |
| AZURE_OPENAI_DEPLOYMENT_NAME | No | Azure OpenAI deployment name | |
| AZURE_OPENAI_EMBEDDING_API_KEY | No | Separate API key for embeddings | |
| AZURE_OPENAI_EMBEDDING_ENDPOINT | No | Separate endpoint for embeddings | |
| AZURE_OPENAI_USE_MANAGED_IDENTITY | No | Use Azure managed identity for auth | false |
| AZURE_OPENAI_EMBEDDING_API_VERSION | No | API version for embeddings | |
| AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME | No | Deployment name for embeddings |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gifflet/graphiti-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server