mnemos
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MNEMOS_LOG_LEVEL | No | The logging level for the server. Possible values: debug, info, warn, error. | info |
| MNEMOS_PROJECT_ID | No | Scope memories to a specific project. This allows mnemos to separate knowledge across different coding projects. | |
| MNEMOS_EMBEDDINGS_API_KEY | No | The API key required if using a cloud-based embedding provider like 'openai'. | |
| MNEMOS_EMBEDDINGS_PROVIDER | No | The embedding provider used for semantic search. Options are 'noop' (text-only search), 'ollama' (local), or 'openai'. | noop |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mnemos_compileC | Distill knowledge into a compiled article |
| mnemos_contextC | Assemble relevant context for a query within token budget |
| mnemos_deleteA | Soft-delete a memory |
| mnemos_getC | Get a memory by ID |
| mnemos_maintainB | Run decay, archival, and GC maintenance |
| mnemos_relateC | Create a relation between two memories |
| mnemos_runtimeA | Report the live MCP server runtime identity: version, host, pid, executable, uptime, data dir, and project scope |
| mnemos_searchB | Search memories using hybrid text+semantic search |
| mnemos_storeC | Store a new memory in Mnemos |
| mnemos_updateB | Update a memory (PATCH semantics) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| load_context | Load relevant context at session start |
| save_session | Save important learnings at session end |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Current project context from mnemos memory base | Pull-based auto-inject for Codex and other non-hook clients |
| Live Mnemos MCP runtime identity | Reports the live MCP server version, process identity, executable, uptime, data dir, and project scope |
| Storage statistics | Overall storage statistics |
TDQS
Scored across 10 tools
Each tool has a clearly distinct purpose: CRUD operations (store, get, update, delete), search, maintenance, relation creation, context assembly, compilation, and runtime info. No two tools overlap in functionality, ensuring an agent can easily select the correct tool.
All tools follow a consistent 'mnemos_' prefix with an underscore-separated verb or noun. Most use imperative verbs (compile, delete, get, maintain, relate, search, store, update), while 'context' and 'runtime' are nouns. This minor inconsistency prevents a perfect score.
With 10 tools, the surface is well-scoped for a memory/knowledge server. It covers essential CRUD, search, maintenance, relations, and advanced features like compilation and context assembly without being overwhelming or sparse.
The tool set covers the full memory lifecycle (create, read, update, soft-delete) plus advanced operations (compile, context, relate, maintain, runtime). Minor gaps include missing batch operations or explicit undo for soft-delete, but the core domain is well-served.