DEV Community: Jay Elsheikh

How I listed my MCP on the official MCP Registery and how you can do yours too ?

Jay Elsheikh — Mon, 10 Aug 2026 11:25:49 +0000

When people ask “where do I find MCP servers?”, a growing chunk of the answer starts in one place: the Official MCP Registry at registry.modelcontextprotocol.io.

I recently listed ThinkReview MCP there — our hosted server that runs AI code reviews on GitHub, GitLab, Azure DevOps, and Bitbucket PR/MR URLs from Cursor, Claude, and Copilot.

Here’s exactly what I did, and how you can do the same.

First, what the registry actually is

The Official MCP Registry stores metadata, not your binaries.

That means:

You don’t upload a zip of your server
You publish a server.json that describes your MCP
Clients and other directories can discover you from that record

There are two common shapes:

Package-based — your server lives on npm / PyPI / NuGet / Docker, and the registry points at that package
Remote / hosted — your server is a public URL (Streamable HTTP), and the registry points at that endpoint

ThinkReview is remote. Our endpoint is:

https://mcp.thinkreview.dev/v1

So I didn’t need to publish an npm package just to get listed. I only needed a solid public docs repo + a valid server.json.

Docs that mattered:

The registry is still in preview. Expect possible breaking changes before GA.

Step 1 — Put something public on GitHub

Directories and developers want a repo they can open.

I created a public visibility/docs repo:

github.com/Thinkode/thinkreview-mcp

It includes:

What the MCP does
Endpoint + transport
OAuth and Bearer setup for Cursor / Claude / Copilot
Example configs

It does not include our private review engine, auth, or billing backend. For a SaaS MCP, that’s the right split:

Public: docs + configs + registry metadata
Private: the actual product

If you’re building an open-source local MCP, your full source can live in that same repo.

Step 2 — Install the publisher CLI

brew install mcp-publisher
mcp-publisher --help

Or grab a binary from the registry releases.

You’ll use three commands most of the time:

mcp-publisher init
mcp-publisher login ...
mcp-publisher publish

Step 3 — Choose your namespace (this is the gotcha)

Your server name is tied to how you authenticate.

Auth method	Name format	Example
GitHub login	`io.github.<user-or-org>/...`	`io.github.Thinkode/thinkreview`
Domain proof (DNS/HTTP)	reverse-DNS of your domain	branded names under your company domain

I used the GitHub org namespace because it’s the fastest path:

io.github.Thinkode/thinkreview

Note: the registry name (thinkreview) and the GitHub repo name (thinkreview-mcp) do not have to match. Pick a clean registry name; point repository.url at whatever public repo you use for docs or source.

Later, you can move to a branded domain namespace if you want cleaner naming — that needs DNS TXT or a /.well-known/mcp-registry-auth proof on your domain.

Step 4 — Create `server.json` for a remote MCP

In the repo:

cd thinkreview-mcp
mcp-publisher init

Then edit the file for a hosted server. Skip packages unless you also ship a local install. Use remotes instead:

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.Thinkode/thinkreview",
  "title": "ThinkReview",
  "description": "Live PR/MR code reviews via review_url_code. OAuth or portal Bearer auth.",
  "version": "1.3.0",
  "websiteUrl": "https://thinkreview.dev/features/mcp",
  "repository": {
    "url": "https://github.com/Thinkode/thinkreview-mcp",
    "source": "github"
  },
  "remotes": [
    {
      "type": "streamable-http",
      "url": "https://mcp.thinkreview.dev/v1"
    }
  ]
}

A few rules that saved me time:

Prefer "type": "streamable-http" (SSE is deprecated)
The URL must be publicly reachable
version is required, unique per publish, and immutable once published — use semver
name must match your auth namespace (io.github.Thinkode/... if you logged in as that org)

Commit server.json so the listing is reproducible.

Step 5 — Authenticate

For the GitHub namespace path:

mcp-publisher login github

You’ll get a device code, authorize it in the browser, and the CLI confirms you’re logged in.

That login only lets you publish under io.github.<that-account-or-org>/....

Step 6 — Publish

mcp-publisher publish

When it works, you’ll see something like:

Publishing to https://registry.modelcontextprotocol.io...
✓ Successfully published
✓ Server io.github.Thinkode/thinkreview version 1.3.0

That’s it. Your MCP is now in the official upstream registry.

Step 7 — Verify

Search by a short token that matches your listing:

curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=thinkreview"

Or use the exact registry name:

curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.Thinkode/thinkreview"

You should see metadata like:

name: io.github.Thinkode/thinkreview
version: 1.3.0
status: active
remote: https://mcp.thinkreview.dev/v1
repository: https://github.com/Thinkode/thinkreview-mcp

From there, community directories (PulseMCP, Glama, mcp.so, mcpservers.org, etc.) often pick listings up over time — but the official registry is the upstream source you want first.

How to keep it updated

Every meaningful MCP release:

Bump version in server.json
Commit
Run mcp-publisher publish again

Or automate it in GitHub Actions with mcp-publisher login github-oidc on version tags so every release republishes metadata.

If something fails

Error	What it usually means
No permission to publish this server	Your `name` doesn’t match your GitHub/domain auth
Invalid or expired JWT	Re-run `mcp-publisher login github`
Registry validation failed	Package listings need ownership proof (`mcpName`, etc.). Remote listings need a live public URL
Version already exists	Bump semver — published versions can’t be overwritten
Search returns empty	You’re searching the wrong string (e.g. repo name vs registry `name`)

The short version

Make a public repo (docs + examples is enough for remote MCP)
Install mcp-publisher
Add a server.json with remotes pointing at your hosted URL
mcp-publisher login github
mcp-publisher publish
Verify with the registry API

That’s how ThinkReview MCP got onto the official MCP Registry — and the same path works whether you’re shipping a local open-source server or a hosted product like ours.

If you’re listing a remote MCP too, start with the GitHub namespace, get discoverable fast, then brand the namespace later once DNS/domain proof is worth the extra step.

ThinkReview MCP: run live PR code reviews from Cursor, Claude Code, and Copilot

Jay Elsheikh — Fri, 07 Aug 2026 10:52:48 +0000

You already use Cursor, Claude Code, or GitHub Copilot to write and refactor code. What if the same assistant could run a real ThinkReview analysis on a pull request—without you copying diffs into chat?

Today we are introducing ThinkReview MCP: a hosted Model Context Protocol server at mcp.thinkreview.dev/v1. Connect it once, then ask your assistant to review any PR or merge request URL on GitHub, GitLab, Azure DevOps, or Bitbucket. ThinkReview fetches the changed files, runs the review, and returns structured feedback: summary, suggestions, security notes, best practices, and suggested follow-up questions.

Why MCP for code review?

Browser extensions are great when you are already on a PR page. MCP is for the moments when you are in the editor or terminal and want review context without context-switching.

Typical flow:

You are pairing with an AI agent on a fix or feature branch.
A teammate shares a PR link in Slack or a ticket.
You ask: “Call review_url_code for https://github.com/org/repo/pull/42.”
ThinkReview returns the same quality of review you would get from the extension—grounded in the actual diff, not a guess from partial snippets.

One tool, one URL, no patch upload. That is the whole idea.

What you need before connecting

ThinkReview MCP is designed to be quick to set up, but two things must be in place:

1. Your ThinkReview Bearer token

Generate or copy your personal token from the MCP integration page in the ThinkReview portal. It is the same authorization token used by the ThinkReview browser extension. Add it to your MCP client as:

Authorization: Bearer <your-token>

If you regenerate the token, update every MCP client (and expect the extension to need the new token too).

2. Git credentials in the portal (required)

MCP cannot fetch a PR diff without git access. Before your first review, add a Personal Access Token under Settings → Integrations in the portal.

ThinkReview uses that PAT to call your git host’s API—same as URL-based reviews in the cloud. If integrations are missing, or the token cannot reach a private org repo (for example SSO not authorized on GitHub), reviews will fail with a clear access error instead of a vague API failure.

This step is easy to skip when you are excited to wire up Cursor—but it is the most common reason MCP reviews do not work on the first try.

The `review_url_code` tool

ThinkReview MCP exposes a single tool today:

Tool	What it does
`review_url_code`	Runs a live code review on a PR or MR URL

Required: prUrl — the full pull or merge request link.

Optional: language (response language), mrId (your tracking ID), forceRegenerate (bypass cache when the PR has new commits but you want a fresh review immediately).

Reviews use the same credits as the browser extension. Results are cached per user when the changed-file fingerprint has not changed, so re-asking about the same PR is fast and does not burn credits unnecessarily.

Custom review agents you configure in the portal are not run by default through MCP—the tool returns the main structured review. Agent workflows remain centered in the extension and portal today.

Connect in minutes

The portal MCP setup page includes copy-paste configs for:

Cursor — add thinkreview under mcpServers with the hosted URL and Bearer header
Claude Code — JSON config or a one-line CLI claude mcp add command
GitHub Copilot (VS Code) — .vscode/mcp.json or user MCP config with the servers key

Example for Cursor:

{
  "mcpServers": {
    "thinkreview": {
      "url": "https://mcp.thinkreview.dev/v1",
      "headers": {
        "Authorization": "Bearer <your-token>"
      }
    }
  }
}

Restart your client after saving. Then try a prompt like: “Review this PR with ThinkReview: https://github.com/org/repo/pull/123.”

Full setup details, security notes, and troubleshooting live in our docs: MCP Integration.

Smarter caching and clearer errors

This release ships alongside improvements to the URL review pipeline MCP uses under the hood:

Commit-aware caching — reviews refresh when the PR’s changed-file list changes, not only when you force regeneration
Actionable git errors — private repo or token issues surface as access-denied guidance (check integrations, org access, GitHub SSO) instead of opaque 404s

Try it today

If you already use ThinkReview in the browser, MCP is the natural next step for AI-native workflows:

Configure git integrations in the portal
Copy your MCP token and client config
Ask your assistant to call review_url_code on your next PR

ThinkReview remains open source for the browser extension. Explore the project and install links on thinkreview.dev.

Extension repository: github.com/Thinkode/thinkreview-browser-extension
Chrome Web Store: ThinkReview — AI copilot for pull requests
Firefox Add-ons: ThinkReview on Firefox

Lookin forward to your feedback , any questions would love to hear

original post :

Code Review bots clutter PRs , anybody feel the same?

Jay Elsheikh — Fri, 24 Jul 2026 01:42:46 +0000

I'd like to get your thoughts if anybody feel the same about code review bots like bugbot , gitlab duo , code rabbit and others that auto post comments on your behalf vs a tool like ThinkReview that shows the review to the reviewer only while the reviewer is still responsible for their final comments

anybody feel the same about how much cluttered the PR gets with these bots ?

Zero setup code reviews for gitlab and azure devops

Jay Elsheikh — Tue, 09 Jun 2026 12:31:31 +0000

Jay Elsheikh

Jun 9

Agentic code reviews without setup on Azure devops PRs

2 min read

Agentic code reviews without setup on Azure devops PRs

Jay Elsheikh — Tue, 09 Jun 2026 12:30:55 +0000

Hello peer developers,

I’m sharing a workflow I built over the past few weeks that has made our pull request security reviews more consistent and more actionable.

ThinkReview is a browser extension that works across Git platforms (Gitlab, Github , azure devops and Bitbucket )and runs a custom review checklist based on what your team cares about, such as OWASP guidance and your internal secure coding standards.

Below is a quick look at the end result, then I’ll walk through how I set it up

Example: a pentesting-focused review agent

In this example, I created a review agent focused on pentesting.

Define the agent’s goal and scope (what kinds of issues it should look for).
Provide a reference the agent should follow, such as STRIKE Graph best practices. https://www.strikegraph.com/blog/pen-testing-best-practices

You can create up to 10 review agent

Run the review on a PR and get findings mapped back to the reference.

In the PR shown here, ThinkReview flagged a couple of OWASP-related issues using the reference we provided.

The project is open source on Github : https://github.com/Thinkode/thinkreview-browser-extension

and you can install it from

chrome webstore : https://chromewebstore.google.com/detail/thinkreview-ai-code-revie/bpgkhgbchmlmpjjpmlaiejhnnbkdjdjn

firefox :

https://addons.mozilla.org/en-US/firefox/addon/thinkreview-code-review

Lookin forward to your feedback , any questions would love to hear

How I set up automated AI code reviews on Azure devops (under 60 seconds) with no CI or coding

Jay Elsheikh — Tue, 02 Jun 2026 22:59:52 +0000

I built an open source Browser extension called ThinkReview to work seamlessly with Azure DevOps — a tool that automatically reviews Pull Requests using any LLM, whether cloud-based or on premise (TFS) without leaving your browser

And the best part?

1- Opensource:

https://github.com/Thinkode/thinkreview-browser-extension

2- Works on your browser (Chrome , Edge or Firefox )

3- It works out of the box on dev.azure.com and company.visualstudio.com

4- If you have on premise ADO with custom domain, All you need is to add the custom domain and your PAT in the extension

5- Chat with your Pull Requests

7- All while on the same page of your PR

I focused on the Ease of Setup and to still maintain the human factor rather than a bot that auto post cluttered comments that developers can miss
Setup takes less than 60 seconds without the need for any coding or integration with CI
It doesn’t spam your PR with Bot comments which will clutter your PR
You won’t need to leave your azure PR page or change to a different tool
Supports legacy Azure on premise formely known TFS down to 2016

Try It Out
Install from Chrome Web Store:

👉 ThinkReview: AI Code Reviews for Azure DevOps

Firefox users:

👉 ThinkReview on Firefox

I Built a One-Click Bridge from Azure Devops PRs Code Review Directly to Cursor/Claude Code

Jay Elsheikh — Sat, 18 Apr 2026 00:36:54 +0000

Hi Everyone ,

I’d like to share here a new feature that I implemented in ThinkReview extension workflow which utilises cursor deeplinks with one click to implement critical bugs , best practices or security issues from the code review

ThinkReview is an opensource browser extension that supports Gitlab , Github , Azure Devops and Bitbucket.

In this demo it generates a code review for a Github PR.
I decided to implement one of the best practices it outlined.
I already use cursot , I will click on the cursor button and with one click it will open cursor and implement it

First Go to any PR and select which IDE agent you want to use currently (Cursor , CLaude code and Github copilot are supported but much more to come )

check the code review generated and select one of the points you'd like to implement , here I'm selecting one of the best prctices about moving magic numbers to constants

Once you click the implement via button in my case here I selected cursor , it will open cursor with your prompt ready to be sent

First thing it will check if we are on the correct branch of the PR
otherwise it will stop and ask you to switch to the correct branch manually

here it identified correctly we are not on the correct branch so I'm going to switch to the correct branch manually

Here it implemented the best prctice in the right branch and I was happy to commit and push the code

here I regenerated the review again and I see the best practices scoring has gone up from 90 to 95
Yay

ThinkReview is open source and you can install the extension from Chrome Store and Firefox addons
https://github.com/Thinkode/thinkreview-browser-extension
https://thinkreview.dev

Bitbucket cloud AI Code Review

Jay Elsheikh — Mon, 13 Apr 2026 21:26:28 +0000

Hi everyone,

I’m excited to announce that I’ve extended the support of ThinkReview browser extension to support Bitbucket Cloud and Bitbucket DataCenter. This extension performs code reviews on your Pull Requests in the browser

The extension is open-source and powered by Ollama, along with the latest frontier LLMs.

Github Repo https://github.com/Thinkode/thinkreview-browser-extension

*Chrome extension : *

https://chromewebstore.google.com/detail/thinkreview-ai-code-revie/bpgkhgbchmlmpjjpmlaiejhnnbkdjdjn

Firefox extension :

https://addons.mozilla.org/en-US/firefox/addon/thinkreview-code-review

For Bitbucket cloud :

You need to generate a bitbucket API Token with scopes (read:repository:bitbucket , read:pullrequestBitbuket)
In ThinkReview extension you will need to add your email and API token there
your email and token is saved locally in your browser local storage and never sent to the cloud

Here's how to create the API token for Bitbucket cloud
https://thinkreview.dev/docs/bitbucket-integration

For Bitbucket data center

you need to go to extension settings
Add custom domain of your bitbucket
Add http access token (https://thinkreview.dev/docs/bitbucket-data-center)

Referenced article :
https://thinkreview.hashnode.dev/bitbucket-cloud-datacenter-ai-code-review-browser-extension

Bitbucket PR AI Code Review and copilot

Jay Elsheikh — Sun, 15 Feb 2026 20:25:37 +0000

ThinkReview now supports Bitbucket Cloud

We're happy to announce that ThinkReview now works with Bitbucket Cloud (bitbucket.org). You can run AI-powered code reviews directly on your Bitbucket Pull Requests, alongside GitLab, GitHub, and Azure DevOps.

ThinkReview is open source and supports local Ollama models, so you can run reviews on your own hardware with no data leaving your machine—or use cloud models if you prefer.

What this means for you

Bitbucket Pull Requests — The extension detects PR pages on bitbucket.org and shows the ThinkReview review panel.
Same experience — Use the AI Review button; ThinkReview fetches the diff and runs the review in the sidebar with suggestions, security notes, and best practices.
One-time setup — Create a Bitbucket API token (or App password) in your Bitbucket settings, then paste it in the ThinkReview popup under the Bitbucket section. Optionally add your Bitbucket account email for Basic auth when required.

How it works

Create a Bitbucket token — In Bitbucket: Personal settings → App passwords / API tokens → Create with at least Repository: Read. Copy the token.
Open ThinkReview → Settings → Bitbucket section. Paste your token (and optionally your account email), then click Save Token.
Open any Pull Request on bitbucket.org and use the AI Review button (e.g. on the bottom right or in the PR toolbar).

ThinkReview will analyze the diff and show suggestions, security notes, and best practices in the sidebar.

Full setup guide

Step-by-step instructions (including token creation) are in the docs:

Bitbucket Integration Guide

Troubleshooting

"Bitbucket API token required" — Open the ThinkReview popup, add or update your token (and email if needed) in the Bitbucket section, save, then try the review again.
401/403 errors — Check that your token has at least Repository: Read and that it hasn’t expired. You can use an API token or an App password.
AI Review button not showing — Reload the Bitbucket PR page after saving your token.

If you hit any issues or have feedback, open an issue on Github or reply in Discussions—we’d love to hear from teams using Bitbucket Cloud.

The Open Source PR code review copilot for Gitlab & ADO that Supports Ollama (without CI/CD setup)

Jay Elsheikh — Sat, 15 Nov 2025 00:20:24 +0000

Hey Developers,
I'd like to announce Thinkreview an AI Copilot that integrates within Pull requests pages on Gitlab and Azure Dev ops

✅ ThinkReview is now fully open source
⚙️ ThinkReview now supports Ollama (local LLMs)

If you’ve been following my earlier Dev.to posts, you know ThinkReview originally launched as a Chrome extension powered by cloud LLMs. It’s grown a lot since then — and the community asked for two things consistently:

Open Source

Local Model Support (Ollama)

Both are finally here.

⚡️ New Feature: Ollama Support (Local LLM)

Up to version 1.3.10, ThinkReview ran exclusively on cloud models.

Starting with v1.4.0, you can now connect ThinkReview to Ollama and run ANY local LLM you want:

Qwen Coder
Llama 3
Codestral
Deepseek
Gemma

Anything Ollama supports

Why this matters:

Your code never leaves your machine
Zero API keys needed
100% free
Great for companies with strict security/compliance
Perfect for self-hosted GitLab users

⚙️ How to enable Ollama

One-time setup:

Stop any existing Ollama processes

Restart Ollama with flags that allow Chrome extension access

Go to ThinkReview settings → Test Connection
and youm should see the models already downloaded

and finally thats how it looks like
(supporting Gitlab and Azure Devops)

To install the extension (open source) you can install directly from Chrome store
https://chromewebstore.google.com/detail/thinkreview-ai-code-revie/bpgkhgbchmlmpjjpmlaiejhnnbkdjdjn

works on Edge too and any chromium browser

Azure DevOps PR AI Code Review: Finally, A Simple Solution

Jay Elsheikh — Tue, 28 Oct 2025 19:24:09 +0000

azuredevops #codereview #chromeextension #ai

Like many developers working with Azure DevOps, I've spent countless hours manually reviewing Pull Requests. I've tried various AI-powered code review tools, all promising to make the process easier. While some were helpful, they all shared the same frustrating issues: complex setup processes, API token management, webhook configurations, and constant dashboard-switching.

I kept asking myself: "Why isn't there a simple azure devops pr ai review solution that just works?"

So, I decided to build one.

After successfully launching ThinkReview for GitLab, Today, I'm excited to share that ThinkReview now supports Azure DevOps Pull Requests with the same simplicity and power that made it popular for GitLab users.

Here's why ThinkReview is the best azure devops copilot pr review alternative you've been looking for:

1. Zero Configuration Required

This remains my top priority. No API tokens to generate, no webhooks to configure, no Azure DevOps app installations. Simply install the Chrome extension, Set your Personal access Token in the extension ,open any Azure DevOps Pull Request, and get instant AI-powered code reviews. It's that simple.

If you've tried setting up other azure devops pr ai review tools, you know the pain of OAuth flows, personal access tokens, and service connections. ThinkReview eliminates all of that.

2. Works Directly in Azure DevOps UI

I designed ThinkReview to stay exactly where you work. The AI review appears directly within your Azure DevOps Pull Request page. No separate dashboards, no third-party platforms, no context-switching.

You can:

Read comprehensive PR summaries
Ask follow-up questions about the code
Get instant explanations of complex changes
Review AI suggestions without leaving Azure DevOps

3. Generous Free Tier

Whether you're a solo developer, a startup team, or exploring azure devops pr ai code review for the first time, ThinkReview offers a genuinely useful free tier. You get real AI-powered insights without any financial commitment upfront.

4. Multi-Language Support

Set your preferred language once in the extension settings, and all AI feedback, summaries, and suggestions will automatically appear in your chosen language. No more language barriers in code reviews.

5. AI Suggested Comments & Smart Questions

Beyond just reviewing code, ThinkReview generates professional code review comments and suggests insightful questions. This feature helps teams:

Maintain consistent review standards
Ask better questions during reviews
Speed up the review process
Improve code quality discussions

Why Azure DevOps Developers Need This

If you're working in the Microsoft ecosystem with Azure DevOps, you know that options for AI-powered PR reviews are limited. While GitHub Copilot works great for GitHub, Azure DevOps users have been underserved.

ThinkReview bridges this gap. It's built specifically to work seamlessly with Azure DevOps Pull Requests, understanding the platform's unique structure and workflow.

Getting Started is Ridiculously Easy

Install the ThinkReview Chrome extension
Navigate to any Azure DevOps Pull Request
See instant AI analysis and insights
Ask questions, get suggestions, improve your code

That's it. No complicated setup, no configuration files, no admin approval needed.

Perfect for Azure DevOps Teams

Whether you're a solo developer maintaining open-source projects, a small startup team, or part of a larger organization using Azure DevOps, ThinkReview scales with your needs. The tool works across:

Azure DevOps Services (cloud)
Azure DevOps Server (on-premises)
All repository types and sizes
Public and private repositories

The Future of Azure DevOps PR AI Review

I built ThinkReview because I was frustrated with the complexity of existing solutions. The response from the GitLab community was overwhelming, and I'm excited to bring the same simplicity to Azure DevOps users.

If you've been searching for a straightforward azure devops pr ai code review tool that actually delivers on its promise of simplicity, I invite you to try ThinkReview.

It's the solution I wish I had when I was struggling with manual code reviews and complicated AI tools.

Try it today and experience what azure devops copilot pr review should have been from the start.

You can install the extension from the Chrome Web Store: ThinkReview: AI Code Reviews for GitLab & Azure DevOps

Available for Chrome, Edge, Opera, Brave, and all Chromium-based browsers.

you could check the latest release notes on

What's your biggest pain point with Azure DevOps Pull Request reviews? Let me know in the comments – I'm always looking to make ThinkReview better for the developer community.

Chat with your MR in Gitlab

Jay Elsheikh — Sat, 18 Oct 2025 23:00:00 +0000

Why settle for static code reviews when you can have a conversation?

The Problem We All Know Too Well

You open a GitLab merge request. 437 lines changed across 12 files. You know you should review it thoroughly, but...

// You, staring at the diff:
"Where do I even start? 🤔"
"What changed and why?"
"Are there security issues I'm missing?"
"How do I ask the right questions?"

Sound familiar?

Traditional code reviews are one-directional: you read the code, leave a comment, done. But what if code review was a conversation?

Meet Your New Code Review Partner

ThinkReview is a conversational AI copilot that lives inside your GitLab merge request pages. But here's the game-changer:

🤔 Smart Follow-Up Questions

After analyzing your MR, ThinkReview suggests 3-5 contextually relevant questions you can click to explore:

Example questions for a typical MR:

🤔 Smart Follow-Up Questions

⬜ Are there any potential security vulnerabilities?
⬜ How will this affect database performance?
⬜ What happens if the API call fails?
⬜ Can you generate a summary comment for the team?
⬜ Are there edge cases we should test?

The magic? These aren't generic. They're generated based on your actual code changes.

Why This Changes Everything

1. Lower Cognitive Load

Before:

You: *stares at 437 lines*
You: "Hmm... what should I check?"
You: *spends 10 minutes thinking*
You: "I'll just approve it"

With ThinkReview:

AI: "Here are 5 things you should explore"
You: *click click click*
You: *actually finds 2 real issues*

2. Junior Developers Learn Faster

The suggested questions become a mentorship tool:

# Junior dev sees:
"What are the performance implications of this code?"

# Junior dev thinks:
"Oh! I should be looking at performance!"

# Junior dev learns:
# Pattern recognition for future reviews

3. More Thorough in Less Time

5 minutes of clicking = what used to take 30 minutes:

✅ Security? Click
✅ Performance? Click
✅ Edge cases? Click
✅ Architecture? Click

Real Example: Catching a Security Issue

The Setup

You're reviewing an authentication feature MR. 186 lines changed.

Step 1: Get AI Review

Click ThinkReview. Within seconds:

## Summary
Implements JWT-based user authentication.

## Key Changes
- Added auth middleware
- JWT token generation/validation
- Protected routes

## Smart Follow-Up Questions
⬜ Are there any potential security vulnerabilities?
⬜ How will this affect API performance?
⬜ What happens if the token expires during a request?

Step 2: Click "Security vulnerabilities?"

ThinkReview responds:

Based on my analysis, I've identified 2 security concerns:

1. **SQL Injection Risk (Line 45)**

javascript
const query = SELECT * FROM users WHERE id = ${userId};

   ❌ User input not sanitized
   ✅ Fix: Use parameterized queries

2. **Missing Auth Check (Line 78)**

javascript
app.post('/api/admin/delete', deleteUser);

   ❌ No permission verification
   ✅ Fix: Add authentication middleware

Would you like me to show you how to fix these?

Step 3: Keep the Conversation Going

You: "How do I implement parameterized queries in Express?"

AI: *provides specific code examples*

You: "Can you generate a comment for the team?"

AI: *creates formatted GitLab comment*

Generate Professional Team Comments

After your AI conversation, click to generate a summary:

## Code Review Summary

### Overview
JWT authentication implementation with security considerations.

### Key Changes
✅ Auth middleware (auth.js)
✅ Token generation/validation
✅ Protected routes

### Issues Found
1. 🔴 CRITICAL: SQL injection vulnerability (Line 45)
   Recommendation: Use parameterized queries

2. ⚠️ HIGH: Missing authentication check (Line 78)
   Recommendation: Add auth middleware

3. 💡 SUGGESTION: Consider refresh token mechanism

### Verdict
Changes needed before approval.

@developer Please address the security issues above.

Copy. Paste. Done. ✨

The Tech Stack

AI Model: Google Gemini 2.5 Pro
Context-Aware: Understands language, framework, file relationships
Privacy: HTTPS-only, no code storage
Works Everywhere: Chrome, Edge, Brave, all Chromium browsers

Common Questions

Q: Won't this make devs lazy?
A: Opposite! It makes reviews more thorough. Suggested questions expose blind spots.

Q: Does it work with self-hosted GitLab?
A: Yes! Works with both gitlab.com and private instances.

Q: How accurate is it?
A: Powered by Gemini 2.5 Pro. Excellent accuracy. But AI complements, not replaces, human judgment.

Try the Challenge

Install ThinkReview (2 min)
Open any GitLab MR
Click 3 suggested questions
Compare to your usual review process

I bet you'll find something you would've missed.

The Bottom Line

Code review shouldn't feel like homework. It should feel like pair programming with an expert who:

✅ Understands your code deeply

✅ Suggests what to look for

✅ Answers instantly

✅ Helps you learn

✅ Makes it enjoyable

Stop reading code. Start conversing with it.

Links

🚀 Install ThinkReview

What's your biggest code review pain point? Drop a comment below 👇

Built by developers who got tired of spending hours on code reviews that should take minutes.

ThinkReview - AI Copilot for GitLab & Azure DevOps | Free Chrome Extension

Transform your GitLab & Azure DevOps workflow with AI-powered code reviews. Get instant analysis, security insights, and code suggestions. Free Chrome extension for developers.

thinkreview.dev

DEV Community: Jay Elsheikh

How I listed my MCP on the official MCP Registery and how you can do yours too ?

First, what the registry actually is

Step 1 — Put something public on GitHub

Step 2 — Install the publisher CLI

Step 3 — Choose your namespace (this is the gotcha)

Step 4 — Create server.json for a remote MCP

Step 5 — Authenticate

Step 6 — Publish

Step 7 — Verify

How to keep it updated

If something fails

The short version

Links

ThinkReview MCP: run live PR code reviews from Cursor, Claude Code, and Copilot

Why MCP for code review?

What you need before connecting

1. Your ThinkReview Bearer token

2. Git credentials in the portal (required)

The review_url_code tool

Connect in minutes

Smarter caching and clearer errors

Try it today

Code Review bots clutter PRs , anybody feel the same?

Zero setup code reviews for gitlab and azure devops

Agentic code reviews without setup on Azure devops PRs

Agentic code reviews without setup on Azure devops PRs

Example: a pentesting-focused review agent

How I set up automated AI code reviews on Azure devops (under 60 seconds) with no CI or coding

I Built a One-Click Bridge from Azure Devops PRs Code Review Directly to Cursor/Claude Code

Bitbucket cloud AI Code Review

For Bitbucket data center

Bitbucket PR AI Code Review and copilot

ThinkReview now supports Bitbucket Cloud

What this means for you

How it works

Full setup guide

Troubleshooting

The Open Source PR code review copilot for Gitlab & ADO that Supports Ollama (without CI/CD setup)

Azure DevOps PR AI Code Review: Finally, A Simple Solution

azuredevops #codereview #chromeextension #ai

you could check the latest release notes on

Chat with your MR in Gitlab

The Problem We All Know Too Well

Meet Your New Code Review Partner

🤔 Smart Follow-Up Questions

Why This Changes Everything

1. Lower Cognitive Load

2. Junior Developers Learn Faster

3. More Thorough in Less Time

Real Example: Catching a Security Issue

The Setup

Step 1: Get AI Review

Step 2: Click "Security vulnerabilities?"

Step 3: Keep the Conversation Going

Generate Professional Team Comments

The Tech Stack

Common Questions

Try the Challenge

The Bottom Line

Links

ThinkReview - AI Copilot for GitLab & Azure DevOps | Free Chrome Extension

Step 4 — Create `server.json` for a remote MCP

The `review_url_code` tool