Graph-Mem MCP
by Sathvik-1007
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GRAPHMEM_DB_PATH | No | Database file path | .graphmem/graph.db |
| GRAPHMEM_MAX_HOPS | No | Default max traversal depth | 4 |
| GRAPHMEM_USE_ONNX | No | Use ONNX runtime if available (true/false) | false |
| GRAPHMEM_LOG_LEVEL | No | Logging verbosity (DEBUG/INFO/WARNING/ERROR/CRITICAL) | WARNING |
| GRAPHMEM_TRANSPORT | No | MCP transport protocol (stdio/sse/streamable-http) | stdio |
| GRAPHMEM_CACHE_SIZE | No | Embedding cache max entries | 10000 |
| GRAPHMEM_BACKEND_TYPE | No | Storage backend | sqlite |
| GRAPHMEM_SEARCH_LIMIT | No | Default search result limit | 10 |
| GRAPHMEM_EMBEDDING_MODEL | No | HuggingFace model ID for embeddings | all-MiniLM-L6-v2 |
| GRAPHMEM_EMBEDDING_DEVICE | No | Inference device (cpu or cuda) | cpu |
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
- 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/Sathvik-1007/GraphMem-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server