MemoryGuard MCP server
io.github.irisxc4/memoryguard·v0.7.12·4 starsLocal-first governed MCP memory backend for coding agents.
4 stars186 downloads/wk
Reviews
Write oneNobody has reviewed MemoryGuard yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
MemoryGuard 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 · 2026-10-15 · same rubric, same numbers if you re-run it
- Code scan215 source files scanned15/25
- –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 15 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
Findings (2)
- mediumeval / new Function used
exec.evalagent_memguard-0.7.12/src/memoryguard/desktop_executor.py: …_force() try: root.eval("tk::PlaceWindow . center") exce… - mediumsubprocess with shell=True
exec.shell-trueagent_memguard-0.7.12/src/memoryguard/rules/skill_rules.py: …"脚本含 rm -rf / curl | sh subprocess.call(shell=True)" negative_example = "脚本只做只读分析,无写操作…
How MemoryGuard compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 74/100
- higher than 40% of 48,243 servers
- GitHub stars
- 4
- more than 82% of 28,706 servers
- Downloads a week
- 186
- more than 74% of 12,306 servers with a package
Install MemoryGuard in Claude Code, Cursor or VS Code
claude mcp add memoryguard -- uvx agent-memguard
What the publisher says
From the MemoryGuard repository's README, as published. We do not edit it. Read it on GitHub
MemoryGuard
<!-- mcp-name: io.github.irisxc4/memoryguard -->
Governed shared memory for coding agents. Local-first MCP memory with automatic organization, scoped rules, evidence, and rollback.
中文文档
Let agents write without turning shared memory into an unreviewed pile.
MemoryGuard organizes each write, preserves the evidence behind changes, and
keeps governance decisions reversible.
**No account. No remote server. No remote telemetry. Local-only usage telemetry
is optional and stores bounded, privacy-preserving aggregates locally.**
Quick start · Upgrade · Knowledge Library · Architecture · Supported hosts · Privacy and safety
A synthetic governed projection: signals move through memory categories while raw conversation text remains outside the graph.
What's New in v0.7.12
v0.7.12 improves MCP discovery, bounded read delivery, and local usage telemetry while preserving the existing governed action checks and MCP name:
day-to-day tools from tools/list, including capability discovery and the governed invocation broker. memoryguard_capabilities provides paginated metadata for registered MCP operations and reviewed headless GUI operations; exact advanced MCP names remain callable for compatibility.
- Compact discovery with a complete catalog: New MCP clients receive 11
UTF-8 bytes across the complete MCP envelope. Eligible oversized reads return a short-lived process-local reference rather than truncating data; reads that cannot be safely replayed or exceed the snapshot limit return a bounded narrowing hint. Pages support UTF-8 offsets and field selection. Private references revalidate the original read under the current trusted session and binding before each page. Writes and context bootstrap keep their complete receipt/mandatory-rule contracts and cannot request response paging.
- Bounded read delivery: Replayable successful reads are capped at 24,000
input counts are kept separately with complete/partial/unavailable coverage. A measured zero remains zero; missing provider data remains unknown. The deterministic unit estimate is labeled as an estimate and does not claim a measured token reduction.
- Cache-aware local telemetry: Provider-reported cache-read and cache-write
and a non-empty idempotency key, which are forwarded to the target's existing permission, scope, and readiness checks. The MCP name remains io.github.irisxc4/memoryguard.
- Governed invocation: Mutating broker targets still require confirmation
See the v0.7.12 release note and release history.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-09-19restoreC → Bscore 74: eval / new Function used; subprocess with shell=True
MemoryGuard: common questions
- Is MemoryGuard MCP server safe?
- Mostly: it is graded B (74/100). Read the MemoryGuard safety report
- How do I install MemoryGuard?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does MemoryGuard need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is MemoryGuard maintained?
- The last commit was 36 days ago (2026-09-30). The latest release is v0.7.12.
- What can I use instead of MemoryGuard?
- Servers from other publishers that do the same job: Deja Vu MCP server, Memorix MCP server and Nautilus Compass Memory MCP server. Compare all MemoryGuard alternatives.
- How does MemoryGuard compare with other MCP servers?
- safety score 74/100 (higher than 40% of 48,243 servers); github stars 4 (more than 82% of 28,706 servers); downloads a week 186 (more than 74% of 12,306 servers with a package). Full comparison.
Alternatives to MemoryGuard
Same job from other publishers: the closest match first, then the best rated.
- Deja Vudeja-vu: local memory over the session histories of forty-three coding agents.not reviewedEstablishedA
MemorixLocal-first project memory with legacy MCP and 2026 discovery compatibility.not reviewedEstablishedB- Nautilus Compass MemoryLocal-first long-term memory for AI agents, with byte-recomputable signed verification receipts.not reviewedEstablishedB