claude-code-organizer MCP — Use Cases, Install & Live Demo

Why use it

Key features

Browser dashboard showing every memory, skill, MCP, command, rule across global + project scope
Token budget tracker — see what's actually being preloaded and at what cost
Security scanner: 60 patterns + 9 deobfuscation techniques for tool poisoning
SHA256 baselines — alerts if an MCP's tools change between scans
Duplicate detection and per-project MCP enable/disable

Live Demo

What it looks like in practice

claude-code-organizer.replay ▶ ready

0/0

Install

Pick your client

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

{
  "mcpServers": {
    "claude-code-organizer": {
      "command": "npx",
      "args": [
        "-y",
        "claude-code-organizer"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "claude-code-organizer": {
      "command": "npx",
      "args": [
        "-y",
        "claude-code-organizer"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "claude-code-organizer": {
      "command": "npx",
      "args": [
        "-y",
        "claude-code-organizer"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "claude-code-organizer": {
      "command": "npx",
      "args": [
        "-y",
        "claude-code-organizer"
      ],
      "_inferred": true
    }
  }
}

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

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "claude-code-organizer",
      "command": "npx",
      "args": [
        "-y",
        "claude-code-organizer"
      ]
    }
  ]
}

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

~/.config/zed/settings.json

{
  "context_servers": {
    "claude-code-organizer": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "claude-code-organizer"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add claude-code-organizer -- npx -y claude-code-organizer

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

Use Cases

Real-world ways to use claude-code-organizer

Audit what's preloaded into every Claude Code session

👤 Power users whose context starts half-full before they type ⏱ ~15 min beginner

When to use: Responses feel slow or context fills fast and you suspect too many memories/skills.

Prerequisites

Claude Code installed with existing memories/MCPs — Standard CC setup

Flow

Launch the dashboard

Run npx @mcpware/claude-code-organizer and open the dashboard.✓ Copied

→ Browser opens with all scopes visible
Sort by token cost

In the dashboard, sort memories/skills by token count — what are the top 5 biggest?✓ Copied

→ Clear top-offender list
Prune ruthlessly

Delete or move to project scope the ones that aren't global concerns.✓ Copied

→ Token budget drops

Outcome: Smaller preloaded context, faster sessions, lower per-call cost.

Pitfalls

Deleting a memory that a teammate relies on — If it's team-wide, move to project scope rather than delete

Scan your MCP servers for tool-poisoning attempts

👤 Anyone installing community MCPs ⏱ ~10 min intermediate

When to use: Before or after installing an MCP from an unfamiliar publisher.

Flow

Run the scanner

Scan all configured MCP servers for suspicious patterns in tool descriptions.✓ Copied

→ Report with NEW/CHANGED/CLEAN per server
Investigate flags

For every flagged finding, show the exact tool description and which pattern fired.✓ Copied

→ Explanations linking pattern → evidence
Disable or remove bad actors

Disable the flagged MCP from project scope and re-scan.✓ Copied

→ Clean second run

Outcome: MCPs that try to smuggle instructions via tool descriptions are caught before they compromise a session.

Pitfalls

False positives on legitimate servers using unusual language — Review the pattern match; false positives don't hurt, but re-enable after verifying
Scanner only catches embedded-prompt-style attacks, not all malicious behavior — Still review source for MCPs that execute code on your box

Deduplicate MCP configs across global and project scopes

👤 Developers with layered .mcp.json + ~/.claude configs ⏱ ~5 min beginner

When to use: Same MCP registered twice in different scopes causing odd behavior.

Flow

Detect duplicates

Find MCP servers registered in multiple scopes.✓ Copied

→ List of duplicates with their scopes
Consolidate

Keep the project-scope definition; remove from global.✓ Copied

→ Single canonical entry

Outcome: A cleaner, lower-confusion config.

Combinations

Pair with other MCPs for X10 leverage

claude-code-organizer + jetski

Organizer audits your local config; Jetski audits server-side usage

After organizer trimmed memories, check Jetski's analytics for any drop in tool-call failures.✓ Copied

claude-code-organizer + marm-systems

Move long-lived memory from CC memories into a proper memory MCP

Find memories in CC that are just factual project notes; propose moving them into MARM-Systems via marm_contextual_log.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
list_scopes	(none)	Full audit	free
scan_mcps	(none) or target server	After adding any MCP, or periodically	free (connects to each MCP briefly)
token_report	scope?	Before pruning	free
dedupe	(none)	Config hygiene	free

Cost & Limits

What this costs to run

API quota: None
Tokens per call: Reports: 500-3000 tokens
Monetary: Free
Tip: Run the scanner after every new MCP install — it's the cheapest defense.

Security

Permissions, secrets, blast radius

Credential storage: Reads your CC config files; doesn't transmit

Data egress: Local dashboard only; connects to MCP servers only to read tool definitions

The scanner is pattern-based; it improves odds but does not replace source review of MCPs that run code.
SHA256 baselines only alert on change — initial-install malicious content needs the pattern scan to catch.

Troubleshooting

Common errors and fixes

Dashboard port in use

Kill the previous instance or set a different port via env.

Verify: lsof -i :<port>

Scanner can't reach a stdio MCP

The scanner spawns the same command your client does; make sure the command works from terminal.

Verify: Run the MCP command manually

False positive on an MCP you trust

Review the match, add it to an allowlist in organizer settings if it's clearly benign.

Verify: Re-run scan with allowlist

Alternatives

claude-code-organizer vs others

Alternative	When to use it instead	Tradeoff
Jetski	You want server-side analytics and auth, not local config cleanup	Different concern — runtime vs setup
Manual grep through ~/.claude	You enjoy pain	No scanner, no UI

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills