Your AI agent writes the code. MegaLens checks it before it reaches your git history.
MegaLens adds planning, research, code review, security audit and diff review to your IDE, without replacing your existing workflow. Works with Claude Code, Codex CLI, Cursor, Gemini CLI and Lovable, and with any tool that supports OAuth MCP connectors, such as ChatGPT and Claude.ai. GitHub Copilot is coming soon.
Reviewers from different AI companies check your code on their own, and a judge marks a finding verified only when it can quote the code that proves it. MegaLens is not a linter: it ignores formatting and syntax and looks for logic, security and behaviour bugs. Keep your linter for style. It runs when you or your AI tool ask for a review, so it can catch problems before a branch is pushed. It does not yet gate pull requests automatically.
MegaLens reviews. Your IDE decides what to change.
A check before you push
MegaLens can catch problems before a branch is pushed. A finding is verified only when the judge can quote the code that proves it.
Reviewers from different companies
MegaLens selects up to four reviewers from different AI companies. Each works on its own. Each result names the models that actually took part.
Your first review is free
No card and no API key for the first one. After that, pick a plan or pay as you go. The pricing page has the details.
How it works
Three steps to use MegaLens in your IDE workflows.
Connect MegaLens to your IDE
Add MegaLens in your AI tool’s connection settings.
Ask for a review in your AI chat
Use MegaLens for planning, research, code review and security audits.
Your IDE makes the final call
Read the findings with your AI assistant and decide what to change.
Workflow fit
MegaLens complements your IDE.
MegaLens runs the review on separate models, away from your IDE's own model.
Claude Code
Already in flow
Claude is already in the driver seat
MegaLens adds
Review from outside the main model family
Result
MegaLens adds planning and audits. Claude Code decides what to change.
Codex (OpenAI)
Already in flow
Codex is already driving the session
MegaLens adds
Targeted review without replacing Codex
Result
MegaLens runs the review in parallel. Codex decides what to do with it.
Cursor, Gemini CLI, Lovable
Already in flow
Your editor already has a primary assistant
MegaLens adds
Planning, audit and research.
Result
MegaLens complements your primary assistant instead of becoming another IDE. Your editor remains the final decision-maker.
Setup
One setup, for every plan
Every plan connects to the hosted endpoint with one token.
Using ChatGPT, Claude.ai or another tool with OAuth connectors? You need no token or config block: paste https://megalens.ai/api/mcp as a connector, then sign in and approve. See the steps.
Get your token
Connect to the hosted endpoint with your token. Your first review is free. After that, pick a plan with reviews included, or pay as you go.
Copy your MegaLens token from Settings → MCP setup:
Add MegaLens to your IDE
The CLI helper detects your editor and writes the hosted config:
npm install -g megalens-mcp megalens-mcp setup
Or add it yourself:
Run this once. The --scope user flag makes MegaLens available in every project:
claude mcp add --transport http --scope user megalens \ "https://megalens.ai/api/mcp?ide=claude-code" \ --header "Authorization: Bearer ml_tok_your_token_here"
Or edit ~/.claude.json yourself:
{
"mcpServers": {
"megalens": {
"type": "http",
"url": "https://megalens.ai/api/mcp?ide=claude-code",
"headers": {
"Authorization": "Bearer ml_tok_your_token_here"
}
}
}
}Add to ~/.codex/config.toml. It is TOML, not JSON:
[mcp_servers.megalens]
url = "https://megalens.ai/api/mcp?ide=codex"
http_headers = { "Authorization" = "Bearer ml_tok_your_token_here" }Cursor, Gemini CLI and Lovable each use a different format. Copy the exact block from Cursor, Gemini CLI or Lovable. GitHub Copilot is coming soon.
Choose how reviews are paid
A plan. Plus and Pro include a monthly allowance of reviews, with model usage included, from $19 a month. A review of up to 25,000 tokens of input counts as one; larger ones count one more for every further 25,000. Research and planning count double. The count is worked out from the size of your input as MegaLens estimates it (about 3.5 characters to a token). See plans.
Pay as you go. Prepay credits, no provider key required. The current rate is on the pricing page.
Nothing to add to the config for either. On Free, MegaLens selects two reviewing models. On a plan, MegaLens selects up to four reviewing models.
Start asking for targeted work
MegaLens tools appear after you restart your IDE. Ask for specific work:
Core scopes
Five scopes in one tool.
Planning, research, code intelligence, security audit and diff audit.
Planning
Use MegaLens for serious planning passes before commits, migrations, infra changes, or product decisions.
Research
Ask MegaLens to research a question with models from different companies.
Code review
Code review works on the actual files your IDE sends, so ask it to send the code, not a summary. You can also ask it for architecture and tradeoff checks.
Security audit
Useful for catching security issues before release.
Diff audit
Run a last review of your diff before you merge.
A check before AI mistakes reach your git history.
Your IDE reads the findings and decides what to fix.