Is Madcop safe to use?

Madcop 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.

How do I install Madcop?

Madcop 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 AI clients work with Madcop?

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

Is Madcop actively maintained?

Madcop is actively maintained — last commit was 1 day ago. It has 99 GitHub stars.

Madcop

Name: Madcop
Author: linmy666

vite · by linmy666

MadCop — local-first AI agent desktop workstation (v0.9). Multi-model chat, tool-use, MCP servers, 12 workflow modes, knowledge base, AI design tool, persistent workspace.

99 156.9M/wk GitHub npm

No known CVEs

No license

Actively maintained

Last commit 1d ago

Works with most clients

Transport: stdio, sse, http

0 tools

Grade F

MCPpedia last refreshed this data 3h ago

Edit this pageView history

Developer Tools AI / ML

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": {
    "madcop": {
      "args": [
        "-y",
        "vite"
      ],
      "command": "npx"
    }
  }
}

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/madcop)](https://mcppedia.org/s/madcop)

Read me

What Madcop does

MadCop is a cross-platform desktop application that brings the power of modern LLMs into a private, agentic workflow. It runs as a single Electron binary on macOS, Windows, and Linux, talks to any OpenAI-compatible API endpoint, and keeps your conversations, files, and knowledge base entirely on your machine. No cloud lock-in, no per-seat fees, no data leaving the device.

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.

npx -y 'vite' 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

57/100across 5 weighted dimensions

How we score →

0255075100

−43

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

22 fixed

CVE-2026-53632info · fixed

launch-editor: NTLMv2 hash disclosure via UNC path handling on Windows

### Summary The `launch-editor` NPM package accesses arbitrary paths including Windows UNC paths. When a UNC path is opened, Windows automatically attempts NTLM authentication to the remote host, causing the user’s NTLMv2 password hash to be leaked to an attacker-controlled SMB server. This can result in credential compromise through offline hash cracking. ### Impact If the following conditions are met, an attacker can get the NTLMv2 password hash on the computer that is using the `launch-edit

Affected: >= 0Fixed in 2.14.1source →

CVE-2026-53571high · fixedCVSS 7.5

vite: `server.fs.deny` bypass on Windows alternate paths

### Summary The contents of files that are specified by [`server.fs.deny`](https://vite.dev/config/server-options#server-fs-deny) can be returned to the browser on Windows. ### Impact Only apps that match the following conditions are affected: - explicitly exposes the Vite dev server to the network (using `--host` or [`server.host` config option](https://vitejs.dev/config/server-options.html#server-host)) - the sensitive file exists in the allowed directories specified by [`server.fs.allow`]

Affected: >= 8.0.0Fixed in 8.0.16source →

CVE-2024-52011info · fixed

launch-editor vulnerable to command injection via the crafted request on Windows

### Summary Due to the insufficient sanitization of the `file` argument in the `launchEditor`, an attacker can execute arbitrary commands on Windows by supplying a filename that contains special characters. ### Impact If the following conditions are met, an attacker can execute arbitrary commands on the computer that is using the `launch-editor`: - An attacker can place a file with the malicious filename - An attacker can call the `launchEditor` method with the `file` argument controlled - The

Affected: >= 0Fixed in 2.9.0source →

CVE-2026-39365info · fixed

Vite Vulnerable to Path Traversal in Optimized Deps `.map` Handling

### Summary Any files ending with `.map` even out side the project can be returned to the browser. ### Impact Only apps that match the following conditions are affected: - explicitly exposes the Vite dev server to the network (using `--host` or [`server.host` config option](https://vitejs.dev/config/server-options.html#server-host)) - have a sensitive content in files ending with `.map` and the path is predictable ### Details In Vite v7.3.1, the dev server’s handling of `.map` requests for

Affected: >= 8.0.0Fixed in 8.0.5source →

CVE-2026-39364info · fixed

Vite: `server.fs.deny` bypassed with queries

### Summary The contents of files that are specified by [`server.fs.deny`](https://vite.dev/config/server-options#server-fs-deny) can be returned to the browser. ### Impact Only apps that match the following conditions are affected: - explicitly exposes the Vite dev server to the network (using `--host` or [`server.host` config option](https://vitejs.dev/config/server-options.html#server-host)) - the sensitive file exists in the allowed directories specified by [`server.fs.allow`](https://vi

Affected: >= 8.0.0Fixed in 8.0.5source →

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 Madcop safe to use?: Madcop 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.
How do I install Madcop?: Madcop 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 AI clients work with Madcop?: Madcop is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is Madcop actively maintained?: Madcop is actively maintained — last commit was 1 day ago. It has 99 GitHub stars.

Similar servers

Others in developer-tools / ai-ml

View all →

XcodeBuildMCP97

XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.

6.1k 1

Supabase MCP Server97

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

2.8k 4

XcodeBuildMCP97

A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.

6.1k 2

Context797

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

59.8k 2

MCP Security Weekly

Get CVE alerts and security updates for Madcop 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?

Edit this pageView history

Developer Tools AI / ML

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": {
    "madcop": {
      "args": [
        "-y",
        "vite"
      ],
      "command": "npx"
    }
  }
}

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/madcop)](https://mcppedia.org/s/madcop)

Read me

What Madcop does

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.

npx -y 'vite' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

README

MadCop

A local-first AI agent desktop workstation.

This document explains the why behind the major design decisions — written for product managers and reviewers who want to understand how the system is put together, not just a list of features.

Preview

Clarify & choose
Interactive question chips · User avatar · Task monitor panel

Structured report output
Markdown tables · Key takeaways · Assistant avatar

Plan-driven execution
Step-by-step planning progress · Live task tracking

What problem is MadCop solving?

The dominant LLM desktop clients (ChatGPT, Claude.ai, Gemini) are excellent chat surfaces but they assume a specific shape of interaction: one human, one model, one conversation at a time, with vendor-managed tools and memory. That works for "answer this question" but it does not work for "I need to (a) search the web, (b) read a local file, (c) summarise the result, (d) save a Markdown report to disk" — which is a normal afternoon for a product manager, analyst, or engineer.

MadCop is built around three observations:

The work is multi-step. A single useful task almost always needs several LLM calls with intermediate state. A chat that cannot sequence, branch, persist, or call external tools caps you at "Q&A on a webpage".
The data is local. A working file directory, a Notion export, a git history, screenshots, contracts — the substance of real work sits on the user's disk. A client that can only attach a single file per message (or pays per-token for cloud RAG) punishes the people who already have the answer.
The model is a choice, not a vendor. A senior engineer might need different models for different tasks — one for refactoring code, another for Chinese-language analysis. A privacy-sensitive user wants a self-hosted endpoint. A startup wants to A/B-test cost. A single-vendor client forces that decision at sign-up and never lets you revisit it.

So the design goal is: a thin local shell that lets the user pick their own model, hand it their own files, and let the system orchestrate the rest. Everything else is in service of that.

How is the system structured?

┌─────────────────────────────────────────────────────────┐
│                    Electron Shell                       │
│  ┌────────────────────┐   ┌────────────────────────┐  │
│  │  Vue 3 + Pinia +   │   │   Python Backend       │  │
│  │  Tailwind v4 UI    │   │   (FastAPI + Uvicorn)  │  │
│  │  (Renderer Process)│←→│                         │  │
│  └────────────────────┘   │  ┌──────────────────┐  │  │
│                            │  │  LLM Client       │  │  │
│  ┌────────────────────┐   │  │  (OpenAI Compat)  │  │  │
│  │  Workspace Picker  │   │  └──────────────────┘  │  │
│  │  Sidebar / Tabs    │   │  ┌──────────────────┐  │  │
│  │  Chat / Composer   │   │  │  Tool Registry    │  │  │
│  └────────────────────┘   │  │  + MCP Bridge      │  │  │
│                            │  └──────────────────┘  │  │
│                            │  ┌──────────────────┐  │  │
│                            │  │  Workflow Engine  │  │  │
│                      

... [View full README on GitHub](https://github.com/linmy666/madcop#readme)

Loading README…

Scored, not listed

Why this score

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

Score breakdown

57/100across 5 weighted dimensions

How we score →

0255075100

−43

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

22 fixed

CVE-2026-53632info · fixed

launch-editor: NTLMv2 hash disclosure via UNC path handling on Windows

Affected: >= 0Fixed in 2.14.1source →

CVE-2026-53571high · fixedCVSS 7.5

vite: `server.fs.deny` bypass on Windows alternate paths

Affected: >= 8.0.0Fixed in 8.0.16source →

CVE-2024-52011info · fixed

launch-editor vulnerable to command injection via the crafted request on Windows

Affected: >= 0Fixed in 2.9.0source →

CVE-2026-39365info · fixed

Vite Vulnerable to Path Traversal in Optimized Deps `.map` Handling

Affected: >= 8.0.0Fixed in 8.0.5source →

CVE-2026-39364info · fixed

Vite: `server.fs.deny` bypassed with queries

Affected: >= 8.0.0Fixed in 8.0.5source →

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 Madcop safe to use?: Madcop 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.
How do I install Madcop?: Madcop 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 AI clients work with Madcop?: Madcop is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is Madcop actively maintained?: Madcop is actively maintained — last commit was 1 day ago. It has 99 GitHub stars.