Skip to content Home / Servers / minnimemory minnimemory MCP Server Curated, on-demand memory for AI coding agents. Cuts Claude Code token cost per session.
minnimemory scores 55 (Fair), with no SPDX license recorded. It installs as a local process. It does not declare tools yet. Filed under AI and memory. Install configs are generated for 10 clients. Being listed in the registry is not the same as being vendor-official.
0 2 Trust score 55 of 100, Fair Fair trust 55 of 100 from six public signals. Nobody can buy a point.
How we score trust Where the 55 comes from 22 + 20 + 0 + 0 + 10 + 3 = 55. Each factor is capped, so no single signal can carry a listing.
Active in the official MCP registry, plus a known vendor namespace.
Registry: 22 of 30 points. How recently the repository saw a commit or release.
Maintenance: 20 of 20 points. Install Pick your client, copy the config, paste it in.
~/Library/Application Support/Claude/claude_desktop_config.json Copy { "mcpServers" : { "minniai-com-minnimemory-plugin" : { "command" : "npx" , "args" : [ "-y" , "minnimemory@1.3.7" ] } } } 0 / 20
GitHub stars and weekly downloads, on a log scale.
Popularity: 0 of 20 points.
A clear, OSI-style open-source license.
License: 0 of 10 points. Not archived, a secure install path, a pinned version.
Security: 10 of 10 points. A real summary, a README with depth, listed tools.
Docs: 3 of 10 points.
Environment variables This server does not declare environment variables.
Tools show up when the registry metadata or the repository README lists them. GitHub enrichment fills this in when a token is configured.
About Curated, on-demand memory for AI coding agents. Cuts Claude Code token cost per session.
FAQ
? What is minnimemory?Curated, on-demand memory for AI coding agents. Cuts Claude Code token cost per session.
? How do I install minnimemory?Pick a client above and copy the generated config. Cursor and VS Code also have a deep link when the server can run locally or remotely.
? Is minnimemory official?No. Registry-listed is not the same as vendor-official. Read the methodology for the difference.
? How is the trust score calculated?This listing scores 55 (Fair). The formula is published on the methodology page. Reviews No reviews yet. Used it? Tell the next person how it went.
Sign in to review this server.
stars
Mi 74 Trust score 74 of 100, Good
Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.
HR 74 Trust score 74 of 100, Good
Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
74 Trust score 74 of 100, Good
Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.
KS 73 Trust score 73 of 100, Good
Shared project memory for Claude Code, Codex and Cursor: decisions and corrections through MCP.
73 Trust score 73 of 100, Good
Code graph and project memory for coding agents, cited to exact files and lines, on your machine.
