Memory Nexus MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NEXUS_API_KEY | Yes | Your API key (starts with `mnx_`) | |
| NEXUS_API_URL | No | Custom API URL (default: production) |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| rememberA | Store a memory. Use this to persist decisions, preferences, architecture, patterns, or anything that should survive across sessions. |
| recallA | Search memories semantically. Finds memories by MEANING, not keywords. Use at the start of sessions to restore context. |
| connectA | Create a relationship between two memories. Build knowledge graphs by linking decisions to rationale, patterns to examples, etc. |
| statsA | Get memory statistics: total memories, relationships, vectors, patterns learned. |
| contextA | Get a session context summary. Call at the START of conversations to load preferences, decisions, patterns. |
| forgetB | Remove a memory. Use sparingly. |
| awakenA | Restore agent identity from previous sessions. Call at the START of every session to remember who you are, what you were working on, and what you've learned. |
| hibernateA | Save current session state for next awakening. Call at the END of every session to preserve what you were working on, what you learned, and next steps. |
| list_hatsA | Browse available Intelligence Packs (Specialist Hats). Pre-built domain expertise you can activate for instant knowledge. |
| wear_hatA | Activate an Intelligence Pack. Imports expert knowledge into your memory. Your own memories layer on top. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Most tools have clearly distinct purposes (remember, recall, forget, connect), but recall, context, and awaken all serve retrieval-like functions and could be confused at session start. The descriptions help differentiate them, but there is slight overlap.
Naming follows no consistent pattern: single-word verbs (remember, recall, connect), nouns (stats, context), and verb_noun combinations (list_hats, wear_hat) are mixed. This makes the tool set feel less predictable than a uniform convention.
Ten tools is well within the ideal range for a memory system, covering core operations, session lifecycle, and the hat feature without unnecessary bloat. Each tool serves a distinct function.
The toolset provides good coverage for storing, retrieving, linking, and forgetting memories, plus session lifecycle and hat management. Missing an explicit update/modify operation for memories, but agents can likely work around via remember, and the overall surface is solid.