Memoria
by ivkond
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEMORIA_HOST | No | Bind host for the HTTP server | 0.0.0.0 |
| MEMORIA_PORT | No | Bind port for the HTTP server | 8080 |
| MEMORIA_MCP_PATH | No | MCP endpoint path | /mcp |
| MEMORIA_AUTH_MODE | No | Auth mode: local, stub_auth, or oidc | local |
| MEMORIA_LOG_LEVEL | No | Application log level | INFO |
| MEMORIA_QDRANT_URL | No | Full Qdrant URL; overrides host/port mode | |
| MEMORIA_QDRANT_HOST | No | Qdrant host when not using a full URL | qdrant |
| MEMORIA_QDRANT_PORT | No | Qdrant port when not using a full URL | 6333 |
| MEMORIA_MEM0_VERSION | No | mem0 API/config version passed to the SDK | v1.1 |
| MEMORIA_LOCAL_USER_ID | No | Fixed user id used in local mode | local-user |
| MEMORIA_OIDC_AUDIENCE | No | Expected access token audience | |
| MEMORIA_OIDC_JWKS_URL | No | Optional internal JWKS URL for server-side verification | |
| MEMORIA_MEM0_GRAPH_URL | No | Memgraph connection URL | bolt://memgraph:7687 |
| MEMORIA_MEM0_LLM_MODEL | No | LLM model name | gpt-4o-mini |
| MEMORIA_QDRANT_API_KEY | No | API key for managed Qdrant deployments | |
| MEMORIA_QDRANT_ON_DISK | No | Enables on-disk Qdrant storage mode | false |
| MEMORIA_OIDC_ISSUER_URL | No | Expected token issuer and default upstream OIDC issuer | |
| MEMORIA_PUBLIC_BASE_URL | No | Public base URL used in advertised MCP/OAuth metadata | http://localhost:8080 |
| MEMORIA_MEM0_LLM_API_KEY | No | LLM API key; local OpenAI-compatible stacks can use any non-empty value | dummy |
| MEMORIA_USER_HEADER_NAME | No | Identity header used in stub_auth mode | x-user-id |
| MEMORIA_MEM0_ENABLE_GRAPH | No | Enables graph memory support in mem0 | false |
| MEMORIA_MEM0_LLM_BASE_URL | No | Optional base URL override for the LLM provider | |
| MEMORIA_MEM0_LLM_PROVIDER | No | LLM provider passed to mem0 | vllm |
| MEMORIA_OIDC_SUBJECT_CLAIM | No | Claim used as the per-user identity | sub |
| MEMORIA_MEM0_EMBEDDER_MODEL | No | Embedder model name | text-embedding-3-small |
| MEMORIA_MEM0_GRAPH_PASSWORD | No | Memgraph password | memgraph |
| MEMORIA_MEM0_GRAPH_PROVIDER | No | Graph provider name | memgraph |
| MEMORIA_MEM0_GRAPH_USERNAME | No | Memgraph username | memgraph |
| MEMORIA_MEM0_HISTORY_DB_PATH | No | Local history DB path used by mem0 | ./data/mem0_history.db |
| MEMORIA_OIDC_REQUIRED_SCOPES | No | Optional space-separated scopes enforced by the verifier | |
| MEMORIA_MEM0_EMBEDDER_API_KEY | No | Embedder API key; local compatible stacks can use any non-empty value | dummy |
| MEMORIA_QDRANT_EMBEDDING_DIMS | No | Embedding dimension size for the collection | 1536 |
| MEMORIA_MEM0_EMBEDDER_BASE_URL | No | Optional base URL override for the embedder provider | |
| MEMORIA_MEM0_EMBEDDER_PROVIDER | No | Embedder provider passed to mem0 | openai |
| MEMORIA_OIDC_PUBLIC_ISSUER_URL | No | Browser-facing issuer for advertised OAuth endpoints | |
| MEMORIA_QDRANT_COLLECTION_NAME | No | Collection name used by mem0 | mem0 |
| MEMORIA_OIDC_JWKS_CACHE_TTL_SECONDS | No | JWKS cache TTL in seconds | 300 |
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/ivkond/memoria'
If you have feedback or need assistance with the MCP directory API, please join our Discord server