MCP.Market

Nexusmem MCP server

by yaminbkk·io.github.yaminbkk/nexusmem·v0.10.5·15 stars
No reviews yet

Local-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP.

A89/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A89/100

full report

Adoption
Growing

15 stars79 downloads/wk

Reviews

Write one

Nobody has reviewed Nexusmem yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Nexusmem tools (6, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • get_status

    Report how many nodes NexusMem currently remembers for a repository, broken down by kind and source.

  • list_recent_memory

    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_suggestions

    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repository -- candidates flagged by "nexusmem stale --check-contradictions" (or automatically during sync) as likely superseded by a newer, similar node.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_suggestion

    "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.

  • search_memorywrite action

    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_project

    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.

Public scan report

scanner v0.1.10 · 2026-10-14 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 17 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 89/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Nexusmem compares

Against every graded Developer tools MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
89/100
higher than 80% of 1,119 Developer tools servers
Tools
6
the typical Developer tools server has 7
Tools that change things
17%
typical: 5%. Fewer write tools means less an agent can break
GitHub stars
15
more than 86% of 855 Developer tools servers
Downloads a week
79
more than 52% of 436 Developer tools servers with a package

What its tools let an agent do: 4 read · 2 change

Install Nexusmem in Claude Code, Cursor or VS Code

Runs npx -y nexusmem on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add nexusmem -- npx -y nexusmem
Add to Cursor

What the publisher says

From the Nexusmem repository's README, as published. We do not edit it. Read it on GitHub

NexusMem

Your coding agent can read git log. It cannot read the four things you tried last Tuesday that didn't work.

NexusMem records what actually happened on your machine (shell commands and their exit codes, git history down to the patch of each changed file, project docs, optionally your assistant transcripts) into a local SQLite database, and serves back a ranked, token-budgeted slice of it on demand. Everything stays on disk. No account, no cloud, no telemetry.

The shell history is the part worth caring about. Git tells an agent what shipped. Shell history tells it what was attempted, in what order, and which commands exited non-zero. That information exists nowhere else, and it disappears when your terminal scrollback rolls over.

Contents: Try it · Exact shell capture · Failure → fix chains · How retrieval works · Session summaries · GitHub issues & PRs · Use it from an agent · What it costs you · Staleness & provenance · Where it breaks · Commands · Cross-project recall · On disk · Development

Try it

From inside any git repository:

npx nexusmem init
npx nexusmem sync

Then ask it something. Real output from this repository, top 2 of 5 hits:

$ nexusmem query "windows spawn failure"

Relevant history for: windows spawn failure

- 2026-08-09 [observed] fix: distinguish a failed git spawn from "not a git repository"
  readRepoInfo collapsed three unrelated failures into one error: git running and reporting
  the path is not a work tree, git not being installed, and the process failing to spawn at
  all. Dogfooding hit the third case in two separate sessions...
- 2026-08-09 [authored] README.md — Before a tagged release
  - [ ] Retry on transient process-spawn failures on Windows

[observed]/[authored] is the provenance tag (see Staleness & provenance) — a commit is a directly observed event, a doc section is a written claim that could go stale.

A commit and a docs section, ranked against each other, inside whatever token budget you gave it. Nothing was summarized by a model on the way out; the ranker just decided what not to send. (One optional source, session summaries, does run a local model — but at ingest time, never on the way out. What you query is always stored text.)

For a sense of what actually accumulates, here is nexusmem status on this repo after two days:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Nexusmem: common questions

Is Nexusmem MCP server safe?
Yes, by our scan: it is graded A (89/100). Read the Nexusmem safety report
How do I install Nexusmem?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Nexusmem need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Nexusmem maintained?
The last commit was 38 days ago (2026-09-27). The latest release is v0.10.5.
What can I use instead of Nexusmem?
Servers from other publishers that do the same job: Repowise MCP server, Suvadu MCP server and Agent Memory MCP server. Compare all Nexusmem alternatives.
How does Nexusmem compare with other Developer tools MCP servers?
safety score 89/100 (higher than 80% of 1,119 Developer tools servers); tools 6 (the typical Developer tools server has 7); tools that change things 17% (typical: 5%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Nexusmem

Same job from other publishers: the closest match first, then the best rated.

All Nexusmem alternatives →
  • Repowise
    Codebase intelligence for AI coding agents — graph, git history, docs, decisions, code health.
    B
  • Suvadu
    Local shell history and AI agent sessions over MCP: search commands, failures, risk and git changes
    A
  • Agent Memory
    Git-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.
    A
  • Palinode
    Inspectable, correctable project memory in git-versioned Markdown for AI agents.
    C
  • Contentrain
    Git content governance, 23 deterministic MCP tools. Hosted: docs.contentrain.io/developer/mcp-cloud
    C