MARM-Systems MCP — Use Cases, Install & Live Demo

Why use it

Key features

18 tools covering sessions, notebooks, memory recall, context bridging
Semantic search via vector embeddings; auto-classifies content (code/project/book/general)
Cross-client memory: Claude, Qwen, Gemini, any MCP client shares the same store
Three transports: STDIO, HTTP (localhost:8001), WebSocket beta
Local SQLite storage — nothing leaves your machine by default

Live Demo

What it looks like in practice

marm-systems.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "marm-systems": {
      "command": "uvx",
      "args": [
        "MARM-Systems"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "marm-systems": {
      "command": "uvx",
      "args": [
        "MARM-Systems"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "marm-systems": {
      "command": "uvx",
      "args": [
        "MARM-Systems"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "marm-systems": {
      "command": "uvx",
      "args": [
        "MARM-Systems"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "marm-systems",
      "command": "uvx",
      "args": [
        "MARM-Systems"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "marm-systems": {
      "command": {
        "path": "uvx",
        "args": [
          "MARM-Systems"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add marm-systems -- uvx MARM-Systems

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use MARM-Systems

Build persistent memory across sessions on a long project

👤 Anyone working a multi-week effort with an AI ⏱ ~15 min beginner

When to use: You keep re-explaining the same project background every session.

Prerequisites

MARM-Systems installed and running — docker pull lyellr88/marm-mcp-server && docker run -d -p 8001:8001 lyellr88/marm-mcp-server

Flow

Start a session tagged to the project

marm_start with project tag 'dataplatform-migration'. Log that we're migrating from Redshift to Snowflake, deadline end of Q2.✓ Copied

→ Session started; initial entry saved
Drop context as you work

marm_contextual_log: 'Decided to use Fivetran for CDC replication, evaluated Airbyte but config overhead too high.'✓ Copied

→ Auto-classified and stored
Next session, recall

marm_smart_recall 'what did we decide about CDC tooling?'✓ Copied

→ Relevant past decision surfaces

Outcome: Session N+1 starts with all of session 1-N context accessible by query, not re-type.

Pitfalls

Dumping every chat into memory clogs recall — Use marm_contextual_log for decisions and milestones, not every exchange
Vector search misses on jargon — Tag entries explicitly with project names for keyword fallback

Combine with: drift

Share memory across a team using multiple AI assistants

👤 Teams where different members use Claude / Qwen / Gemini ⏱ ~45 min advanced

When to use: Knowledge trapped in one person's AI shouldn't be.

Flow

Run MARM as a shared HTTP server

Deploy MARM-Systems on a team server; each teammate points their MCP client at http://marm.team.internal:8001/mcp.✓ Copied

→ All clients connect
Log shared context

marm_contextual_log: 'Database backup runbook is at /runbooks/db-backup.md; last updated 2026-04-10.'✓ Copied

→ Everyone can recall it
Recall from any client

From a teammate's Qwen session: marm_smart_recall 'how do I restore the DB'?✓ Copied

→ Same answer surfaces

Outcome: Cross-AI shared institutional memory.

Pitfalls

Shared memory needs real OAuth — Don't rely on the dev hardcoded credentials — wire to your IdP before prod use
Sensitive data leaks into shared recall — Use project tags and scope queries by tag

Use notebooks as AI-queryable scratchpads

👤 Learners, researchers ⏱ ~5 min beginner

When to use: You want a topic-scoped note area the AI can search later.

Flow

Create a notebook

marm_notebook_add name='rust-ownership' with entry: 'Move vs borrow: move transfers ownership, borrow lets you peek.'✓ Copied

→ Notebook created
Add as you learn

marm_notebook_add 'rust-ownership': 'Mutable borrow is exclusive; only one at a time.'✓ Copied

→ Entry appended
Recall later

marm_notebook_show 'rust-ownership'✓ Copied

→ Full notebook

Outcome: A queryable learning journal.

Combinations

Pair with other MCPs for X10 leverage

marm-systems + drift

drift remembers code conventions; MARM remembers project decisions

Recall drift conventions AND MARM decisions for project 'dataplatform-migration' and summarize where they interact.✓ Copied

marm-systems + claude-code-organizer

Move short-lived memories out of CC into MARM for long-term recall

Organizer listed my 12 biggest memories — move the 5 project-specific ones into MARM notebooks.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
marm_start	project?, tags?	Start of any working session	free (local)
marm_refresh	session_id?	Reload context mid-session	free
marm_smart_recall	query: str, top_k?: int	Semantic search past entries	free (local embeddings)
marm_contextual_log	text: str, tags?: str[]	Persist a decision/milestone/fact	free
marm_log_session	session_id	Review a past session	free
marm_notebook_add	name: str, entry: str	Topic-scoped notes	free
marm_notebook_use	name: str	Pin a topic for the session	free
marm_notebook_show	name: str	Read a notebook	free
marm_summary	scope: session\|notebook\|tag, id	Condense long history	free (local)
marm_context_bridge	from_session, to_session	Cross-project reasoning	free

Cost & Limits

What this costs to run

API quota: None — local-only
Tokens per call: Recall responses 500-2000 tokens typically
Monetary: Free, open source
Tip: Rotate or archive old sessions periodically — SQLite handles scale but recall quality degrades with noise.

Security

Permissions, secrets, blast radius

Credential storage: Local SQLite; for shared HTTP mode use env-based OAuth secrets

Data egress: None by default (local storage); if you run shared, only within your network

Never grant: Exposing port 8001 to the public internet without an auth layer

Dev mode ships hardcoded OAuth credentials — change before any shared deployment.
Memory can accumulate sensitive data; back up and encrypt the SQLite file.

Troubleshooting

Common errors and fixes

Cannot connect to localhost:8001

Container not running. docker ps to check; docker start marm-mcp-server.

Verify: curl http://localhost:8001/docs

Embeddings model download fails

First run downloads the model; needs outbound net. After that, offline works.

Verify: Check docker logs for HuggingFace download

Recall returns unrelated entries

Too few entries for good embeddings; add more, or pre-filter by tag.

Verify: marm_smart_recall with tag filter

Alternatives

MARM-Systems vs others

Alternative	When to use it instead	Tradeoff
drift	You want code-specific memory (conventions, decisions)	Code-focused; less general
Letta (MemGPT)	You want a research-grade memory agent, not just a server	Heavier to run; opinionated architecture
CC native memories	Claude Code only; no cross-client need	No semantic search; bloats context

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills