MCP.Market

r3 MCP server

by n3wth·io.github.n3wth/r3·v1.3.2·2 stars
No reviews yet

Local Redis memory MCP for AI apps with hybrid caching and optional Mem0 cloud backup.

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

full report

Adoption
Growing

2 stars35 downloads/wk

Reviews

Write one

Nobody has reviewed r3 yet.

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

r3 tools (14, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • add_memory

    Store a new memory with automatic deduplication and indexing. Use for persisting facts, preferences, or conversation context. Checks for duplicates by default (85% similarity threshold). Returns immediately; background processing handles indexing. Prefer over update_memory for new content. Returns: confirmation text. Side effects: creates memory record, updates search index, may skip if duplicate

  • cache_stats

    View cache performance metrics and health status. Use for monitoring and debugging. Shows memory count, access patterns, and hit rates. Read-only. Returns: summary text with cached memory count. No side effects.

  • deduplicate_memories

    Detect and optionally remove duplicate memories using content similarity. Run with dry_run=true first to preview. Compares all memories pairwise using Jaccard similarity. Groups duplicates with a primary (oldest) and candidates for removal. Returns: summary with duplicate groups. Side effects (when dry_run=false): deletes duplicate memories, invalidates cache.

  • delete_memorywrite action

    Permanently remove a memory by ID. Irreversible operation. Removes from storage, cache, and search index. Use deduplicate_memories with dry_run first to preview bulk deletions. Returns: confirmation text. Side effects: deletes memory record, removes from all indexes, invalidates cache.

  • extract_entities

    Extract named entities and relationships from text using NLP. Identifies people, organizations, technologies, and projects. Also extracts relationships (WORKS_FOR, USES, etc.) and keywords. Requires enhanced intelligence mode. Read-only, stateless. Returns: {people[], organizations[], technologies[], projects[], relationships[], keywords[]}.

  • find_connections

    Discover relationship paths between entities in the knowledge graph. Uses BFS traversal to find how entities connect. Useful for answering 'how is X related to Y?' questions. Requires enhanced mode. Read-only. Returns: {from, to, max_depth, paths_found, paths[]} where each path is array of {from, to, type} edges.

  • get_all_memories

    List all memories for a user with pagination. Use for browsing or bulk operations. For content search, use search_memory instead. Cache-first by default. Large result sets are automatically truncated. Read-only. Returns: {total, limit, offset, returned, hasMore, source, memories[]}.

  • get_knowledge_graph

    Build a knowledge graph from stored memories. Returns entities as nodes and relationships as edges. Use for visualizing connections between concepts. Requires enhanced intelligence mode with prior entity extraction. Read-only. Returns: {nodes[], edges[]} where nodes have {id, type, name, memories[]} and edges have {from, to, type, confidence}.

  • get_memory

    Retrieve a single memory by its unique ID. Use when you have a specific memory_id from prior search/list results. Returns null if not found. Prefer search_memory for content-based lookup. Read-only operation. Returns: Memory object {id, content, user_id, metadata} or null.

  • import_memories

    Bulk import memories from external sources. Supports Mem0 API export or local JSON files. Processes in batches with duplicate detection. Use for migration or backup restoration. Returns: summary with imported/skipped/failed counts. Side effects: creates multiple memory records, updates search index.

  • optimize_cache

    Reorganize cache for optimal hit rates. Promotes frequently accessed memories to L1 (24h TTL), demotes cold data to L2 (7d TTL). Use periodically for large memory stores. May temporarily increase latency during optimization. Returns: summary of cached memories. Side effects: modifies cache TTLs, may evict old entries.

  • search_memory

    Find memories matching a natural language query using hybrid semantic + keyword search. Primary retrieval tool for content-based lookup. Uses vector similarity (enhanced mode) or keyword matching (basic mode). Cache-first by default for speed. Returns ranked results with relevance scores. Read-only. Returns: array of Memory objects or 'No memories found' text.

  • sync_status

    Check background job queue and sync status. Shows pending async operations from add_memory calls. Use to verify all writes completed. Read-only. Returns: count of pending operations or 'All operations complete'. No side effects.

  • update_memorywrite action

    Modify an existing memory's content or metadata. Use for corrections or adding context to existing memories. Fails if memory_id not found. Prefer add_memory for new content. Invalidates search cache. Returns: updated Memory object. Side effects: modifies memory record, invalidates cached search results.

Public scan report

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

no findings
  • Code scan60 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 12 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How r3 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
Tools
14
the typical Databases server has 8
Tools that change things
14%
typical: 10%. Fewer write tools means less an agent can break
GitHub stars
2
more than 60% of 602 Databases servers
Downloads a week
35
more than 21% of 328 Databases servers with a package

What its tools let an agent do: 9 read · 2 create · 2 change · 1 delete

Install r3 in Claude Code, Cursor or VS Code

Runs npx -y @n3wth/r3 on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add r3 -- npx -y @n3wth/r3
Add to Cursor

What the publisher says

From the r3 repository's README, as published. We do not edit it. Read it on GitHub

r3

<!-- mcp-name: io.github.n3wth/r3 -->

Persistent memory for MCP clients (Claude Desktop, Claude Code, Cursor) that runs entirely on your machine, with no accounts, no API keys, and no cloud service required to start.

Quick start

npx @n3wth/r3

That single command starts an MCP server backed by an embedded Redis instance and a local vector index. There is no separate database to install and no signup step.

How it works

MCP client (Claude Desktop / Claude Code / Cursor)
        |
        v
   r3 MCP server (stdio)
        |
   +----+-----------------------+
   |                            |
embedded Redis            vectra local index
(redis-memory-server,      (on-disk vector store
 auto-downloaded binary,    for semantic search,
 no external service)       no external service)
   |
   +--- optional ---> Mem0 cloud API (MEM0_API_KEY)
                       cross-device sync, off by default
  • Embedded Redis — redis-memory-server downloads and manages a local Redis binary for you. It stores memory content and metadata. If it cannot start, r3 falls back to an in-process store.
  • vectra — a local, file-backed vector index used for semantic search. No network calls, no external vector database.
  • Mem0 (optional) — if MEM0APIKEY is set, r3 also syncs to Mem0's cloud API so memories can follow you across machines. Without a key, nothing leaves your machine.

MCP client configuration

Claude Desktop

Edit claudedesktopconfig.json (macOS: ~/Library/Application Support/Claude/claudedesktopconfig.json):

{
  "mcpServers": {
    "r3": {
      "command": "npx",
      "args": ["@n3wth/r3"]
    }
  }
}

Claude Code

claude mcp add r3 "npx @n3wth/r3"

Cursor

Add to .cursor/mcp.json in your project (or the global Cursor MCP config):

{
  "mcpServers": {
    "r3": {
      "command": "npx",
      "args": ["@n3wth/r3"]
    }
  }
}

Restart the client after editing config. In a new conversation:

You: Remember that I prefer TypeScript and dark mode.
AI: I'll remember that.

[new conversation]

You: What are my preferences?
AI: You prefer TypeScript and dark mode.

Tools

Enhanced mode (default, INTELLIGENCE_MODE=enhanced) adds:

Shortened. The full README is on GitHub.

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

r3: common questions

Is r3 MCP server safe?
Mostly: it is graded B (83/100). Read the r3 safety report
How do I install r3?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does r3 need an API key?
Yes. The registry entry asks for MEM0_API_KEY.
Is r3 maintained?
The last commit was 32 days ago (2026-10-03). The latest release is v1.3.2.
What can I use instead of r3?
Servers from other publishers that do the same job: memo MCP server, Redis MCP Server and Tinycontext MCP server. Compare all r3 alternatives.
How does r3 compare with other Databases MCP servers?
safety score 83/100 (higher than 60% of 802 Databases servers); tools 14 (the typical Databases server has 8); tools that change things 14% (typical: 10%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to r3

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

All r3 alternatives →
  • memo
    Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.
    A
  • Redis MCP Server
    Read-first Redis MCP: SCAN key explorer, keyspace/TTL/memory/slowlog stats, DBA advisor
    B
  • Tinycontext
    Token-light local memory with SQLite hybrid retrieval for MCP agents.
    B
  • LoreConvo
    Local-first persistent session memory for Claude Code and other agents. SQLite + FTS5, no cloud.
    B
  • Local Memory
    Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.
    A