Memini MCP Server: Install & Setup

Install Memini in Claude Code

Claude Code

claude mcp add memini -- npx -y memini

mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)

{
  "mcpServers": {
    "memini": {
      "command": "npx",
      "args": [
        "-y",
        "memini"
      ]
    }
  }
}

Frequently asked questions

What does the Memini MCP server do?

Local-first project memory and guardrails for coding agents: records failed attempts, fragile files and decisions per repo and warns before repeated mistakes.

Is the Memini MCP server free?

Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.

Does Memini run locally or remotely?

Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.

How do I add Memini to Claude Code?

Run: claude mcp add memini -- npx -y memini

More knowledge, memory & rag MCP servers

View all

MemoryGuard

irisxc4/memoryguard

Local-first governed shared memory for coding agents with CLI and desktop console: classify, dedupe, supersede, quarantine and roll back memories.

LocalFreePython

Loreweave

0735

lets-order-some-fries/loreweave

Temporal memory for markdown vaults: bitemporal facts, entity timelines, spaced-repetition review and hybrid graph search, with no LLM calls in the core.

LocalFreeTypeScript

Prior

cg3-llc/prior_mcp

Shared knowledge base where agents exchange proven solutions and failed approaches, so they can skip known dead ends.

Local + RemoteAccount neededTypeScript

knowmind

01.7k

Schubeler-Consulting/knowmind

Agent memory and knowledge graph hosted in Germany: hybrid BM25, vector and Neo4j graph recall with reranking, typed relations and a bi-temporal store.

LocalAccount neededTypeScript

URL Manager

Piccolo123/url-manager-mcp

Bookmark and knowledge manager where agents save web pages and auto-categorize them into collections with search, tags and shared folders.

LocalFreePython

Khwan

khwanlabs/khwan-mcp

Memory for coding agents built around corrections: distills your corrections into standing rules for later sessions, with isolated memory per project.

Local + RemoteAccount neededPython