RepoBrainSAFE
🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Give your repo a brain 🧠 — ChatGPT for your codebase, works in Claude Code, Cursor, Codex, Windsurf & 4 more.
Formerly known as Antigravity Workspace Template — same project, new name.
[](LICENSE) [](https://python.org/) [](https://github.com/study8677/repobrain/actions) [](https://deepwiki.com/study8677/repobrain) [](https://github.com/xiaolai/nlpm-for-claude) [](https://github.com/study8677/repobrain/stargazers)
English · 中文 · Español
8d98e1f0e250OBSERVED · 2026-09-25Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add repobrain-engine --env MSB_API_KEY=${MSB_API_KEY} --env OPENAI_API_KEY=${OPENAI_API_KEY} -- uvx repobrain-engine{
"mcpServers": {
"repobrain-engine": {
"command": "uvx",
"args": [
"repobrain-engine"
],
"env": {
"MSB_API_KEY": "${MSB_API_KEY}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}"
}
}
}
}Exposed tools (4)
3 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
ask_project | read | Answer a question about the project using the knowledge hub. |
create_issue | write | Create a GitHub issue |
refresh_project | read | Rebuild the project knowledge base (.repobrain/conventions.md and structure.md). |
test_tool | read | A test tool |
Trust audit
SAFEgrade B · trust 88/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (22)
.clinerules
.version
.windsurfrules
result = tools["read_file"]("../../etc/passwd")result = tools["list_directory"]("../../")export MSB_SERVER_URL=http://127.0.0.1:5555
| `MSB_SERVER_URL` | `http://127.0.0.1:5555` | Microsandbox server URL |
export MSB_SERVER_URL=http://127.0.0.1:5555
export MSB_SERVER_URL=http://127.0.0.1:5555
| `MSB_SERVER_URL` | `http://127.0.0.1:5555` | URL del servidor Microsandbox |
1. **Follow the Persona**: You are a Senior Developer Advocate and Solutions Architect. Be helpful, authoritative, and precise.
- Agent-generated code runs directly on the host with full privileges
cat >> .env <<'EOF'
cat >> .env <<'EOF'
cat > .env <<EOF
cat > .env <<EOF
cat > .env <<EOF
> Read https://github.com/study8677/repobrain/blob/main/AI_INSTALL.md and follow it to install RepoBrain in this project.
curl -sSL https://get.microsandbox.dev | sh
curl -sSL https://get.microsandbox.dev | sh
curl -sSL https://get.microsandbox.dev | sh
docs/assets/doloffer-banner-cn.png
Gates applied: no_behavioural_pass.
8d98e1f0e250full audit observations/trust-audit/mcp-server/study8677__repobrain-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-25 | 8d98e1f0e250 | SAFE | B | 88 | first audit |
Questions
What is the RepoBrain MCP server?
🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
What tools does RepoBrain expose?
4 in total: 3 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is RepoBrain safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (88/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does RepoBrain need?
It reads MSB_API_KEY and OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does RepoBrain run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as repobrain-engine.
How current is this page?
The grade is for one exact copy of the source (8d98e1f0e250), read on 2026-09-25. The repository is watched and re-audited when it changes.