memory-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEMORY_EMBED_DIM | No | Dimension of the embedding vectors (must match the selected model). | 768 |
| MEMORY_LLM_MODEL | No | Model name for LLM-based tools (e.g., extract_and_remember, get_trends). | llama3.2 |
| MEMORY_AI_API_KEY | No | API key if the provider requires authentication. | |
| MEMORY_AI_TIMEOUT | No | Timeout in seconds for AI calls (embed and LLM). LLM gets max of this and 60. | 30 |
| MEMORY_AI_BASE_URL | No | Base URL for the OpenAI-compatible API endpoint (e.g., Ollama, OpenAI, LM Studio). | http://localhost:11434/v1 |
| MEMORY_EMBED_MODEL | No | Model name for generating embeddings. | nomic-embed-text |
| MEMORY_LLM_BASE_URL | No | Optional separate base URL for LLM calls (split backend). Defaults to MEMORY_AI_BASE_URL. | |
| MEMORY_DECAY_HALFLIFE_DAYS | No | Global default half-life in days for memory confidence decay. | 90 |
| MEMORY_TRUST_DEFAULT_REMEMBER | No | Default trust tier for memories created via the remember tool (1-5). | 5 |
| MEMORY_DECAY_CATEGORY_HALFLIFE | No | JSON object mapping category names to custom half-life days (e.g., {"preference": 180}). | |
| MEMORY_LOCATION_DECAY_HALFLIFE_HOURS | No | Half-life in hours for location memory confidence decay. | 24 |
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
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/brianchilders/memory-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server