Geniro Graphiti MCP
Officialby geniro-io
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Extraction model | gpt-5.5 |
| NEO4J_URI | No | Bolt endpoint for Neo4j | bolt://localhost:7687 |
| NEO4J_USER | No | Neo4j user | neo4j |
| EMBEDDER_DIM | No | Must match the model's output dimension | 4096 |
| LLM_BASE_URL | No | Required for openai_generic (LiteLLM/Ollama/vLLM) | |
| LLM_PROVIDER | No | LLM provider: openai, anthropic, openai_generic | openai |
| EMBEDDER_MODEL | No | Embedding model, not chat model | qwen3-embedding:8b |
| NEO4J_PASSWORD | No | Neo4j password | demodemo |
| OPENAI_API_KEY | No | OpenAI API key (required if using OpenAI provider) | |
| EMBEDDER_BASE_URL | No | Ollama default | http://localhost:11434/v1 |
| EMBEDDER_PROVIDER | No | Embedder provider: openai, ollama, voyage, openai_generic | ollama |
| GRAPHITI_GROUP_ID | No | Optional memory namespace | main |
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 | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues