MCP.Market

sync82 MCP server

by oito2·io.github.oito2/mcp-sync82·v1.3.0

Persistent, structured project memory for AI coding agents, stored locally in SQLite.

B83/100grade B
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed sync82 yet.

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

sync82 tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-10-09 · same rubric, same numbers if you re-run it

no findings
  • –Code scanpackage could not be scannedn/a
  • –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 1 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How sync82 compares

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

Safety score
83/100
higher than 60% of 802 Databases servers

Install sync82 in Claude Code, Cursor or VS Code

The registry entry has no remote endpoint or installable package.

What the publisher says

From the sync82 repository's README, as published. We do not edit it. Read it on GitHub

sync82

🌐 Language: English · Português

sync82 is a Model Context Protocol (MCP) server that gives an AI coding agent persistent, structured memory of a software project across sessions — goals, architecture, tech stack, decisions, and progress, all stored locally and recalled automatically the next time the agent opens the project.

Table of Contents

  • Overview
  • Prerequisites & Quick Installation
  • Client Setup
  • Update & Maintenance
  • Documentation
  • AI Usage in This Project
  • License

Overview

Memory is stored in an embedded SQLite database and ships as a single self-contained binary — no runtime toolchain, no npm package, just sync82 on your PATH. The agent reads and writes it through MCP tools; you talk to the agent in plain language.

  • Six standard memory files per project, plus any custom file, for projects and their subprojects (monorepos, plugin ecosystems).
  • Automatic project discovery — a .sync82.json in the workspace means the agent never has to name the project again.
  • 19 MCP tools — load a whole project's context in one call, save a session in one call, search the whole vault, archive old history, export/import plain Markdown — plus read-only MCP resources with each project's memory and startsession/endsession prompts.
  • One-step client setup — sync82 install registers sync82 in Claude Code, Claude Desktop, Antigravity, Codex, OpenCode, Cursor, Zed and Cline; sync82 uninstall removes it.
  • Local and private — stdio transport only, no network service, one SQLite file per vault.
  • Verifiable releases — SHA-256 checksums, a Sigstore signature and GitHub build provenance attestations; a Claude Desktop extension (sync82.mcpb) and an MCP Registry entry.

Tools (19)

The AI agent calls these over MCP — it never touches the database directly. Full parameter reference in Tools Reference.

Shortened. The full README is on GitHub.

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

sync82: common questions

Is sync82 MCP server safe?
Mostly: it is graded B (83/100). Read the sync82 safety report
Does sync82 need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is sync82 maintained?
The last commit was 27 days ago (2026-10-08). The latest release is v1.3.0.
What can I use instead of sync82?
Servers from other publishers that do the same job: Myc MCP server, open-memex MCP server and Graphmem MCP server.

Alternatives to sync82

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

  • Myc
    Task queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun.
    C
  • open-memex
    Local-first memory for AI coding agents — Markdown + SQLite FTS5, shared across editors via MCP.
    B
  • Graphmem
    Shared local memory for coding agents: SQLite, semantic recall, linked entities, code navigation.
    A
  • SAME - Stateless Agent Memory Engine
    Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
    B
  • skillmem
    Skill memory for coding agents: learn, recall, reinforce, decay. Local SQLite, no API key.
    A