MARM Systems

Name: MARM Systems
Author: Lyellr88

marm-mcp-server · by Lyellr88

Turn AI into a persistent, memory-powered collaborator. Universal MCP Server (supports HTTP, STDIO, and WebSocket) enabling cross-platform AI memory, multi-agent coordination, and context sharing. Built with MARM protocol for structured reasoning that evolves with your work.

306 9 tools GitHub PyPI

No known CVEs

MIT license

Actively maintained

Last commit 7d ago

Works with most clients

Transport: stdio, sse, http

9 tools · ~399 tok

Grade A · 0.2% of 200K ctx

Edit this pageView history

AI / ML Data

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "marm-memory": {
      "httpUrl": "http://localhost:8001/mcp",
      "authentication": {
        "type": "oauth",
        "clientId": "local_client_b6f3a01e",
        "tokenUrl": "http://localhost:8001/oauth/token",
        "clientSecret": "local_secret_ad6703cd2b4243ab",
        "authorizationUrl": "http://localhost:8001/oauth/authorize"
      }
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/marm-systems)](https://mcppedia.org/s/marm-systems)

Read me

What MARM Systems does

alt="MARM - The AI That Remembers Your Conversations."

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

uvx 'marm-mcp-server' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

90/100across 5 weighted dimensions

How we score →

0255075100

−10

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked marm-mcp-server against OSV.dev.

Inventory

Tools (9)

Click any tool to inspect its schema.

~399 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is MARM Systems safe to use?: MARM Systems has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.
How do I install MARM Systems?: MARM Systems supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can MARM Systems do?: MARM Systems provides 9 tools: store_memory, retrieve_memory, session_management, semantic_search, notebook_management and 4 more. See the full tools list on the server page for descriptions and parameters.
What AI clients work with MARM Systems?: MARM Systems is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is MARM Systems actively maintained?: MARM Systems is actively maintained — last commit was 7 days ago. It has 306 GitHub stars.

Similar servers

Others in ai-ml / data

View all →

PostgreSQL MCP Server98

Query and manage PostgreSQL databases directly from AI assistants

87.9k 1

Sequential Thinking MCP Server98

Dynamic problem-solving through sequential thought chains

87.9k 1

Memory MCP Server98

Persistent memory using a knowledge graph

87.9k 5

Supabase MCP Server97

Manage Supabase projects — databases, auth, storage, and edge functions

2.8k 4

MCP Security Weekly

Get CVE alerts and security updates for MARM Systems and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

{ "mcpServers": { "marm-memory": { "httpUrl": "http://localhost:8001/mcp", "authentication": { "type": "oauth", "clientId": "local_client_b6f3a01e", "tokenUrl": "http://localhost:8001/oauth/token", "clientSecret": "local_secret_ad6703cd2b4243ab", "authorizationUrl": "http://localhost:8001/oauth/authorize" } } } }

Why MARM MCP: The Problem & Solution

Your AI forgets everything. MARM MCP doesn't.

MARM MCP is a local memory infrastructure layer for AI agents. It gives Claude, Codex, Gemini, Qwen, IDE agents, and other MCP clients one persistent place to store decisions, retrieve context, reuse notebooks, and keep long-running work from drifting.

The point is not "more tools." MARM exposes 7 focused MCP tools and moves the heavy work behind the server: session routing, protocol delivery, hybrid recall, serialized writes, rate-limit presets, write-time consolidation, and agent-assisted compaction. Because the tool surface stays small, re-ranking filters results before they reach the model, and consolidation catches duplicates at write time, token spend stays low and predictable as workloads grow.

How It Works

Layer

What it does

Why it matters

Memory model

Sessions, structured logs, notebooks, summaries, and semantic memories

Keeps project history searchable instead of trapped in one chat

Scale layer

SQLite WAL mode, connection pooling, serialized write queue, and HTTP rate-limit presets

Lets one server support solo use, multi-agent work, and swarm-style bursts

Intelligence layer

FTS filter, semantic re-rank, bounded semantic fallback, auto-classification, write-time consolidation, and compaction candidates

Keeps recall useful as memory grows instead of letting duplicates pile up

Token layer

Lightweight 7-tool surfa

Frequently Asked Questions

Is MARM Systems safe to use?

MARM Systems has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.

How do I install MARM Systems?

MARM Systems supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What can MARM Systems do?

MARM Systems provides 9 tools: store_memory, retrieve_memory, session_management, semantic_search, notebook_management and 4 more. See the full tools list on the server page for descriptions and parameters.

What AI clients work with MARM Systems?

MARM Systems is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is MARM Systems actively maintained?

MARM Systems is actively maintained — last commit was 7 days ago. It has 306 GitHub stars.

MARM: Local-First Persistent Multi-Agent Memory Layer for MCP Clients v2.15.2

Contributions welcome! Browse open issues to contribute, or join the MARM Discord to share workflows, get setup help, and connect with other builders.

Why MARM MCP
Quick Start
Complete MCP Tool Suite
MARM Dashboard
Performance & Scaling Benchmarks
Contributing
Project Documentation

Why MARM MCP: The Problem & Solution

Your AI forgets everything. MARM MCP doesn't.

How It Works

Layer	What it does	Why it matters
Memory model	Sessions, structured logs, notebooks, summaries, and semantic memories	Keeps project history searchable instead of trapped in one chat
Scale layer	SQLite WAL mode, connection pooling, serialized write queue, and HTTP rate-limit presets	Lets one server support solo use, multi-agent work, and swarm-style bursts
Intelligence layer	FTS filter, semantic re-rank, bounded semantic fallback, auto-classification, write-time consolidation, and compaction candidates	Keeps recall useful as memory grows instead of letting duplicates pile up
Token layer	Lightweight 7-tool surfa

... View full README on GitHub

MARM Systems

Install in your client