mnemostack
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_HOST | No | Ollama server URL for Ollama embeddings and LLM | http://localhost:11434 |
| GEMINI_API_KEY | No | Google Generative AI key for Gemini embedding and Gemini Flash LLM | |
| MNEMOSTACK_LLM | No | LLM provider for answer generation and reranking | |
| MNEMOSTACK_PROVIDER | No | Embedding provider for CLI/HTTP/MCP | |
| MNEMOSTACK_GRAPH_URI | No | Memgraph bolt URI for graph retriever and GraphStore | |
| MNEMOSTACK_BM25_PATHS | No | BM25 corpus paths separated by os.pathsep (':' on Unix) for BM25 retriever | |
| MNEMOSTACK_COLLECTION | No | Qdrant collection name | mnemostack |
| MNEMOSTACK_QDRANT_URL | No | Qdrant server URL for remote Qdrant | http://localhost:6333 |
| MNEMOSTACK_LLM_PROVIDER | No | Alternative LLM provider (alias for MNEMOSTACK_LLM) | |
| MNEMOSTACK_MEMGRAPH_URI | No | Alternative Memgraph bolt URI (alias for MNEMOSTACK_GRAPH_URI) | |
| MNEMOSTACK_AUTO_RECORD_IOR | No | Toggle for HTTP recall exposure logging (true/false) | |
| MNEMOSTACK_EMBEDDING_PROVIDER | No | Alternative embedding provider (alias for MNEMOSTACK_PROVIDER) |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mnemostack_healthA | Check health of all mnemostack components. Read-only, no side effects, no authentication required. Returns a JSON object with ok (bool) and per-component status for the embedding provider, Qdrant vector store, and optional Memgraph graph database. Use this to verify the memory backend is reachable before issuing recall queries. |
| mnemostack_searchA | Search indexed memories with hybrid recall. Read-only, no side effects, no authentication required. Use this when you need raw memory matches rather than a synthesized answer. Returns a JSON object with ok, query, count, results, and degraded (which components fell back while serving the call; empty when healthy). Results are ranked by reciprocal rank fusion of BM25, semantic, graph, and temporal retrievers when configured; each result includes id, text, score, sources, and payload. |
| mnemostack_answerA | Answer a question using retrieved memories. Read-only, no side effects, no authentication required. Use this when you want a concise factual answer synthesized from memory search results instead of the raw matches returned by mnemostack_search. Returns a JSON object with ok, query, answer text, confidence (0.0-1.0), sources, degraded (components that fell back while serving the call), fallback_recommended, and error. |
| mnemostack_feedbackA | Record explicit feedback for stateful recall learning. Use signal='clicked' to also record inhibition-of-return exposure. Pass retriever labels from mnemostack_search results as sources so Q-learning can update source weights. |
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/udjin-labs/mnemostack'
If you have feedback or need assistance with the MCP directory API, please join our Discord server