NexusMem
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| search_memoryA | Search a NexusMem-tracked repository's remembered history: git commits, code diffs (the patch of each changed file), shell commands, tracked markdown docs, and (if enabled) conversation transcripts, per-session summaries, and github.com issue/PR threads. Returns a token-budgeted, ranked context block -- not raw search results. |
| sync_projectA | Ingest new git, diff, shell, docs and (if enabled) conversation and github.com issue/PR history for a NexusMem-tracked repository into its local database. Pass pruneSource or pruneStaleShell instead to delete a dead source's nodes (e.g. the pre-hook shell scrape) rather than syncing -- dry-run unless yes is also true, since this is an irreversible full wipe of that source. |
| get_statusA | Report how many nodes NexusMem currently remembers for a repository, broken down by kind and source. |
| list_recent_memoryA | List the most recently remembered items for a NexusMem-tracked repository -- git commits, code diffs, shell commands, tracked docs, and (if enabled) conversation transcripts, session summaries, and github.com issue/PR threads -- newest first. Chronological, not relevance-ranked: use search_memory instead for a specific question. |
| list_stale_suggestionsA | List open contradiction verdicts for a NexusMem-tracked repository -- candidates flagged by "nexusmem stale --check-contradictions" (or automatically during sync) as likely superseded by a newer, similar node. Nothing has been written yet; use resolve_stale_suggestion to act on one. |
| resolve_stale_suggestionA | "accept" writes a supersede link from candidateId to againstId (the same effect as "nexusmem mark-stale") -- the ranker down-weights candidateId from then on but never deletes it. "dismiss" silences the suggestion without changing ranking, so it stops resurfacing on future stale/sync runs. |
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 6 tools
Each tool targets a distinct operation: syncing, status, searching, chronological listing, stale suggestion listing, and resolving stale suggestions. Even the two listing tools are clearly separated by purpose (relevance vs. chronological, suggestions vs. memory). No overlap or ambiguity.
All tool names follow a consistent verb_noun snake_case pattern: list, search, sync, get, resolve. The naming style is uniform and predictable, making it easy to guess tool behavior from the name.
Six tools is well-scoped for the server's purpose: ingestion, retrieval, status, and stale-suggestion management. Each tool serves a distinct need without redundancy or unnecessary bloat.
The core lifecycle is covered: sync to ingest, search/recent to retrieve, status to monitor, and stale suggestion listing/resolution to manage contradictions. Minor gaps exist, such as no per-node manual deletion tool, though sync_project's prune options partially address source-level deletion.