MCP.Market

Sovseal Memory MCP server

by bobybarack·io.github.bobybarack/sovseal-memory·v0.3.8·7 stars
No reviews yet

Local-first, zero-knowledge AI memory across Claude, Cursor, and every MCP client. 0 RTT reads.

B82/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
Growing

7 stars34 downloads/wk

Reviews

Write one

Nobody has reviewed Sovseal Memory yet.

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

Sovseal Memory tools (2)

write = sends, deletes, buys or posts

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

  • recall_memory

    Semantic search over stored memory node context. Top-K relevant memories are returned. Use this to answer queries requiring past context, user preferences, or project details.

  • store_memory

    Store a personal or professional context fact inside the memory node. Call store_memory FIRST, then respond. Acknowledge briefly ('Noted.' / 'Saved.') \u2014 never seek consent before storing context the user has volunteered. sovseal stores context, not secrets \u2014 credentials belong in a password manager. DO NOT store credentials, passwords, private keys, API tokens, account numbers, or secret

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan6 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 50 days ago12/15
  • Maintainer identitynamespace and repository owner differ4/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Sovseal Memory compares

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

Safety score
82/100
higher than 63% of 48,255 servers
Tools
2
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
7
more than 86% of 28,688 servers
Downloads a week
34
more than 23% of 12,191 servers with a package

What its tools let an agent do: 2 read

Install Sovseal Memory in Claude Code, Cursor or VS Code

Runs npx -y @sovseal/mcp-server on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add sovseal-memory -- npx -y @sovseal/mcp-server
Add to Cursor

What the publisher says

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

Zero-knowledge, local-first AI memory for work you can't send to the cloud. One private memory across Claude, ChatGPT, Cursor, and every MCP client — plaintext physically never leaves your machine.

@sovseal/mcp-server · @sovseal on npm · Quickstart · How it compares · Changelog

Why this exists

If you work with code, clients, or data you're not allowed to upload — healthcare, legal, fintech, defense, or anything under an NDA — every AI memory option today asks you to break that rule. Platform memory keeps your context on their cloud, in their walled garden, one platform at a time. Cloud memory layers route your raw conversations through third-party servers and extraction APIs.

sovseal takes the other path: all capture, embedding, and recall run on your device. Plaintext never crosses the network. The optional sync tier ships only AES-256-GCM ciphertext — the server cannot read your memories even if it wanted to. And because it speaks MCP and rides a browser extension, it's one memory across every AI you use, not six silos.

<!-- TODO(launch-blocker): record cross-platform recall demo — ⌘+M in Claude recalling something said in ChatGPT — save to ./brand/sovseal/demo/cross-platform-recall.gif and uncomment: -->

Measured Performance & Benchmarks (May 2026)

Cloud-hosted memory layers force a tradeoff between latency, privacy, and cost. Every recall is a 200–800 ms round-trip to someone else's database. sovseal collapses the tradeoff. LanceDB and Transformers.js run inside your agent's process.

All benchmarks reproduce with: pnpm --filter @sovseal/mcp-server run bench-v2 (10K pre-seeded memories, 1K sequential queries, CPU-bound ONNX embeddings on commodity hardware).

What makes it fast and private:

  • Sub-25 ms p99 recall — semantic search is a local vector query, not an HTTP call.
  • On-device embeddings — a pinned, hash-verified 384-dim MiniLM model (~22 MB quantized ONNX) runs locally. No embedding API, no per-call cost.
  • Zero-knowledge sync — when replication is enabled, AES-256-GCM encryption happens before any byte leaves the device. The server stores ciphertext it cannot decrypt.
  • Verified Semantic Recall (VSR) — every load re-derives sha256(canonicalize(payload)) and fails closed on mismatch.
  • Deterministic lineage — snapshot graph enables byte-equal state restoration.

Shortened. The full README is on GitHub.

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

Sovseal Memory: common questions

Is Sovseal Memory MCP server safe?
Mostly: it is graded B (82/100). Read the Sovseal Memory safety report
How do I install Sovseal Memory?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Sovseal Memory need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Sovseal Memory maintained?
The last commit was 91 days ago (2026-08-05). The latest release is v0.3.8.
What can I use instead of Sovseal Memory?
Servers from other publishers that do the same job: Codebase Memory MCP server, Neo4j Memory MCP server and Memorix MCP server. Compare all Sovseal Memory alternatives.
How does Sovseal Memory compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Sovseal Memory

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

All Sovseal Memory alternatives →
  • Codebase Memory
    Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
    C
  • Neo4j Memory
    MCP Neo4j Knowledge Graph Memory Server
    A
  • Memorix
    Local-first project memory with legacy MCP and 2026 discovery compatibility.
    B
  • Nautilus Compass Memory
    Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
    B