mcp-zeromem
by cubicecho
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Listen port inside the container (published as 3200). | 3000 |
| DATA_DIR | No | Where the store lives. Also exported to the engine as ZEROMEM_HOME; if both are set they must agree. | /data in the image, ./data on the host |
| EVAL_HISTORY | No | The eval runs the Eval page charts. | docs/eval/history.jsonl |
| ZEROMEM_MODELS | No | Where the model is downloaded to (≈130 MB, once). | <DATA_DIR>/models |
| SECURE_LOCAL_NET | No | true disables auth: for a trusted network only. Set to true to allow the server to start without MCP_ZEROMEM_TOKEN. | |
| ZEROMEM_EMBEDDER | No | The embedder for a new store: auto loads bge-small-en-v1.5 over ONNX and falls back to a hashed embedder, loudly, if it cannot; onnx refuses to start instead; hash never downloads anything; openai uses the endpoint below; none gives this process no dense view. An existing store keeps the embedder it was built with. | auto |
| MCP_ZEROMEM_TOKEN | No | Bearer token for /mcp. The HTTP server refuses to start without one unless SECURE_LOCAL_NET=true. | |
| ZEROMEM_READ_ONLY | No | Hide the write tools. | false |
| ZEROMEM_SESSION_ID | No | Session left out of zeromem_recall by default. | |
| ZEROMEM_EMBEDDING_URL | No | Base URL of an OpenAI-compatible embeddings API, e.g. http://npu-box:11434/v1; required with ZEROMEM_EMBEDDER=openai. | |
| ZEROMEM_EMBEDDING_MODEL | No | Model name sent to that endpoint, e.g. nomic-embed-text. | |
| ZEROMEM_EMBEDDING_API_KEY | No | Bearer token for the endpoint. Overrides a key saved from the Settings page; never returned by the API. | |
| ZEROMEM_EMBEDDING_TIMEOUT_MS | No | Per-request timeout for the endpoint. | 5000 |
| ZEROMEM_ALLOW_EMBEDDER_SWITCH | No | Force an existing store onto ZEROMEM_EMBEDDER at boot: drops every vector and re-embeds in the background. | false |
| ZEROMEM_EMBEDDING_QUERY_PREFIX | No | Prepended to queries, for models that want them (query: for E5). | |
| ZEROMEM_EMBEDDING_DOCUMENT_PREFIX | No | Prepended to stored turns, for models that want them (passage: for E5). |
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
ActivityMaintained
ResponsivenessNo issues