Skip to content
MCP server

MegaLens

Code review by AI models from different companies, showing where they agree and disagree

Install
Pricing
Freemium
Platforms
CLI, API, Web
Runs
Remotely
Version
1.0.0
Listing updated
1 day ago

About MegaLens

MegaLens is a freemium MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.

MegaLens checks what an AI coding agent wrote before it reaches your git history. It selects up to four models from different AI companies to review the code independently, with two on the Free plan, and a judge marks a finding as verified only when it can quote the code that proves it. The result shows where the reviewers agree and where they disagree, and the review runs on MegaLens servers.

It connects over MCP to Claude Code, Codex CLI, Cursor, Gemini CLI and Lovable, to OAuth connector tools such as ChatGPT and Claude.ai by pasting a URL, and to anything else through a REST API; GitHub Copilot is listed as coming soon. A setup wizard run with npx megalens-mcp setup asks for your MegaLens token, detects installed tools and writes their configs, and the README shows each tool's different config format. Lovable uses a form instead of a file.

The first review is free with no card. Bring-your-own OpenRouter key is supported with an extra header. The final choice of what to apply stays with you and your coding agent.

Install

Run in a terminal

claude mcp add --transport http mcp https://megalens.ai/api/mcp

Add to Settings → Connectors → Add custom connector

https://megalens.ai/api/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://megalens.ai/api/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://megalens.ai/api/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://megalens.ai/api/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://megalens.ai/api/mcp"
    }
  }
}

What it does

Multi-company panel
Up to four models from different AI companies review the code.
Verified findings
A judge verifies a finding only if it can quote supporting code.
Agreement view
Reports where reviewers agree and disagree.
Setup wizard
npx megalens-mcp setup detects tools and writes their configs.
Many clients
Works with Claude Code, Codex CLI, Cursor, Gemini CLI, Lovable and OAuth connectors.
REST API
Run reviews from any tool that can make an HTTP request.

Good for

  • Review code an AI agent just wrote before committing
  • Get a second opinion from models of different vendors
  • Check a Lovable-built app
  • Run reviews from ChatGPT or Claude.ai via a connector URL
  • Script reviews through the REST API

Pricing

Freemium

First review free; Free plan uses two reviewing models; paid prices not shown

Prices change. Check megalens.ai before you buy.

MegaLens FAQ

Is there a free tier?

Yes. The first review is free with no card, and Free selects two reviewing models.

Which tools are supported?

Claude Code, Codex CLI, Cursor, Gemini CLI and Lovable, with GitHub Copilot coming soon.

Where does the review run?

On MegaLens servers.

Can I use my own model key?

Yes, the README describes adding your own OpenRouter key through a header.

Is MegaLens free?

MegaLens has a free plan, with paid plans for more usage or features.

How do I add MegaLens to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://megalens.ai/api/mcp

What are the best alternatives to MegaLens?

The closest alternatives to MegaLens are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to MegaLens

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools