$ loading_
Persist project memory and git snapshots across Claude Code sessions.
This MCP tool claims to provide persistent memory and automatic git snapshots; based on that functionality, it likely reads/writes local project data and executes related local commands, but the materials do not show any required secrets or remote egress. Being open source is a positive factor, but low adoption, unknown maintenance, and missing README keep the overall posture at caution.
The materials explicitly state that no keys or environment variables are required, and there is no indication of API tokens, account credentials, or other sensitive authentication material being requested, so credential exposure appears low.
The materials list no remote endpoints, and the description does not mention cloud sync or external API connectivity; based on the available information, there is no explicit user-data egress path shown.
The system checks indicate code execution, and 'automatic git snapshots' suggests it likely invokes local git or related processes on the host. This is a normal tool capability, but it does mean local command execution should be expected.
Its stated persistent-memory and git-snapshot features imply it may read project content and decision records and write local memory/version-control data. There is no evidence of permissions beyond its stated purpose, but local data read/write scope should still be constrained carefully.
The project has public source code, which is a meaningful positive sign for auditability. However, it comes from a third-party registry, has no declared license, shows 0 stars, unknown maintenance status, and a missing README, so the supply-chain signals are relatively weak and warrant repository and dependency review before use.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "memory-mcp" yet — see the docs or source repo.
Please save the key architecture decisions for the current project into memory-mcp, including tech choices, module boundaries, known trade-offs, and follow-up notes.
The tool stores reusable project memory so future sessions can quickly understand the architectural context.
Before I refactor the authentication module, use memory-mcp to create a Git snapshot and record the current implementation patterns and risk areas.
A traceable code snapshot is created with notes on the current implementation for comparison or rollback.
Using the records in memory-mcp, summarize prior decisions about the repository's caching strategy, why they were made, and the constraints I should follow now.
A summary of past caching-strategy decisions is returned to help continue development seamlessly.
Give Claude Code persistent memory, checkpoints, and project sync across sessions.
Add per-repo persistent memory with versioned retrieval for Claude Code.
Persist Claude Code conversations and retrieve relevant context across sessions.
Give Claude Code persistent cross-session memory for project context and preferences.
Persist and recall project context in Claude Code across coding sessions.
Persistently store and retrieve project memory, preferences, and decisions for Claude Code.