repobrain

MCP server · GitHub · ★ 1.4k · graded 2026-10-22Source linked

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

No outside reports on file

RepoBrain gives external AI services access to your entire codebase, creating serious risks for leaked secrets and proprietary code unless you're very careful about what repositories you connect.

Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Repobrain helpful?

What it can access

Local filesNo local folder access notedLOW
Command executionNo shell command runner notedLOW
Network reachConnects to outside service APINOTED
CredentialsRequires API key or tokenREVIEW
Package sourceGitHub (study8677/repobrain)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/study8677/repobrain ↗

All setup options ↓

Check this skill Watch it in my stack Compare Add to allowlist README badge View project

About Repobrain

RepoBrain is an MCP connector that lets AI assistants like Claude analyze and understand your entire codebase. It scans your repository to provide context and help with code questions, refactoring, and development tasks directly in coding tools like Cursor and Windsurf.

Who it’s for

Developers who use AI-powered code editors and want their AI assistant to have deep knowledge of their specific project. It works best for people comfortable connecting their local code repositories to cloud-based AI services.

Alternatives

GitHub Copilot: Built-in code AI that GitHub controls, often integrated into editors
Local LLMs with code indexing: Open-source tools that run AI models on your own machine
Codebase-aware Claude: Use Claude through the web or API with manual code snippets instead of automatic scanning
Tabnine: AI code completion that can work locally or with selective cloud features

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README for installation instructions. The setup likely involves cloning the repository and configuring it as an MCP server in your editor's settings, but exact steps should be verified in the official documentation at https://github.com/study8677/repobrain (opens external site).

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

34/100

GitHub stars: 1.4k
Listing last refreshed: 2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Security reports

No reports found for this package in our research (last checked 2026-10-29).

Check a specific version →

Risks to watch for

Full codebase exposure: The tool uploads or analyzes your entire repository, including private keys, secrets, or proprietary code you didn't intend to share
Secret leaking: If your code contains API keys, passwords, or tokens in comments or configuration files, they may be sent to external AI services
Vendor lock-in and data retention: Code analyzed by the tool may be stored, logged, or used by the service provider to improve their models
Malicious file tricks: Specially crafted code comments or filenames could trick the AI into misunderstanding your codebase or following hidden instructions
No guarantee of privacy: Even if the project claims security, you're trusting a third-party service with your source code

How to lower the risk

Least-privilege permissions

Only connect repositories that contain no secrets, API keys, or private data
Remove sensitive files before connecting your repo

Network isolation

Check what servers the tool contacts before running it
Use a test repository unrelated to production code

Monitoring

Review the tool's logs to see what code was sent where
Audit the project's source code for unexpected data transmission

Red flags to watch for

Tool requests access to files outside the repository directory
No clear documentation about data retention or deletion
Unexplained network requests to unknown services

Questions

How do I install Repobrain?

Repobrain does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/study8677/repobrain.

Are there security reports about Repobrain?

No reports found for this package in our research (last checked 2026-10-29). Repobrain currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include full codebase exposure, secret leaking, vendor lock-in and data retention.

Is Repobrain actively maintained?

Repobrain has 1.4k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/study8677/repobrain before pinning it in production.

What are alternatives to Repobrain?

Notable alternatives to Repobrain include GitHub Copilot (Built-in code AI that GitHub controls, often integrated into editors), Local LLMs with code indexing (Open-source tools that run AI models on your own machine), Codebase-aware Claude (Use Claude through the web or API with manual code snippets instead of automatic review), Tabnine (AI code completion that can work locally or with selective cloud features). You can also compare Repobrain side by side with other MCP servers in the Related tools section on this page.

Maintain or use Repobrain? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

GitHub README Markdown:

markdown

[![AgentArmorHQ Risk Grade for Repobrain](https://agentarmorhq.com/api/badge/study8677-repobrain)](https://agentarmorhq.com/skills/study8677-repobrain)

HTML embed:

html

<a href="https://agentarmorhq.com/skills/study8677-repobrain"><img src="https://agentarmorhq.com/api/badge/study8677-repobrain" alt="AgentArmorHQ Risk Grade for Repobrain" height="20" /></a>

Terminal check:

terminal

curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "study8677-repobrain"

Share with your security lead

Need sign-off to use repobrain? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: repobrain
- **Listing URL:** https://agentarmorhq.com/skills/study8677-repobrain
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.4k GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (study8677/repobrain)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/study8677/repobrain
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type: App connector
Publisher: study8677
Source code: github.com/study8677/repobrain
Est. context load: ~550 tokens / turn (~3 tool schemas, 0.27% of 200k context)
Popularity: 1.4k GitHub stars
Last updated: 2026-10-29
Last graded: 2026-10-22

Community

Discussions for Repobrain

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Repobrain helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude