by LvcidPsyche
Give your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.
# Add to your Claude Code skills
git clone https://github.com/LvcidPsyche/auto-browser
Give your AI agent a real browser, with a human in the loop.
Auto Browser is an MCP-native browser control plane for authorized workflows. It gives MCP clients, LLM agents, and operators a shared Playwright browser with human takeover, reusable auth profiles, approvals, audit trails, and local-first deployment.
Works with:
ALLOWED_HOSTS, auth profile paths, and upload roots/dashboard, noVNC takeover, MCP transport, audit trails, and readiness checksSee CHANGELOG.md for the full release history.
| Browser Control | Operator Safety | Deployment and Integration | | --- | --- | --- | | Playwright-backed sessions with screenshots, DOM summaries, OCR excerpts, tab controls, downloads, and network inspection | approval gates, operator identity headers, audit events, PII scrubbing, Witness receipts, and protection profiles | MCP over HTTP, bundled stdio bridge, REST API, Docker Compose, Codespaces, auth profiles, and optional per-session isolation |
git clone https://github.com/LvcidPsyche/auto-browser.git
cd auto-browser
docker compose up --build
That is enough for local development with the default settings.
Optional:
cp .env.example .env
make doctor
Run make doctor from a normal terminal with local Docker access and permission to open localhost sockets.
Open:
http://127.0.0.1:8000/docshttp://127.0.0.1:8000/dashboardhttp://127.0.0.1:6080/vnc.html?autoconnect=true&resize=scaleAll published ports bind to 127.0.0.1 by default.
Codespaces provisions the stack automatically. The dashboard and noVNC tabs are usually ready in about 90 seconds.
The highest-signal flow in this repo is:
Start here:
Minimal session creation:
curl -s http://127.0.0.1:8000/sessions \
-X POST \
-H 'content-type: application/json' \
-d '{"name":"demo","start_url":"https://example.com"}' | jq
Minimal observation:
curl -s http://127.0.0.1:8000/sessions/<session-id>/observe | jq
Auto Browser exposes:
http://127.0.0.1:8000/mcphttp://127.0.0.1:8000/mcp/tools and http://127.0.0.1:8000/mcp/tools/callscripts/mcp_stdio_bridge.pyThe default MCP tool profile is curated, which keeps the browser surface compact for better tool selection. If you want the full internal tool surface, set:
MCP_TOOL_PROFILE=full
Raw tool-call example:
curl -s http://127.0.0.1:8000/mcp/tools/call \
-X POST \
-H 'content-type: application/json' \
-d '{
"name":"browser.create_session",
"arguments":{
"name":"demo",
"start_url":"https://example.com"
}
}' | jq
Client setup guides:
docs/mcp-clients.mdexamples/claude-desktop-setup.mdexamples/cursor-mcp-setup.mdexamples/claude_desktop_config.jsonFor a real private deployment, set at least:
APP_ENV=production
API_BEARER_TOKEN=<strong-random-secret>
REQUIRE_OPERATOR_ID=true
AUTH_STATE_ENCRYPTION_KEY=<44-char-fernet-key>
REQUIRE_AUTH_STATE_ENCRYPTION=true
REQUEST_RATE_LIMIT_ENABLED=true
METRICS_ENABLED=true
COMPLIANCE_TEMPLATE can apply a preconfigured posture at startup:
| Template | Auth Encryption | Operator ID | PII Scrub | Isolation | Max Session Age |
| --- | --- | --- | --- | --- | --- |
| HIPAA | required | required | all layers | docker_ephemeral | 4h |
| PCI-DSS | required | required | all layers | docker_ephemeral | 1h |
| SOC2 | - | required | network + text | shared | 24h |
| GDPR | - | - | all layers | shared | 24h |
All templates require upload approvals. HIPAA, SOC2, and PCI-DSS also enable Witness receipts. Startup writes the applied policy to /data/compliance-manifest.json.
Example:
COMPLIANCE_TEMPLATE=HIPAA docker compose up
For deployment details, hosted Witness notes, CLI auth modes, and reverse-SSH guidance, see:
flowchart LR
User[Human operator] -->|watch / takeover| noVNC[noVNC]
LLM[OpenAI / Claude / Gemini] -->|shared tools| Controller[Controller API]
Controller -->|Playwright protocol| Browser[Browser node]
noVNC --> Browser
Browser --> Artifacts[(screenshots / traces / auth state)]
Controller --> Artifacts
Controller --> Policy[Allowlist + approval gates]
Core components:
browser-node/ runs Chromium, Xvfb, x11vnc, and noVNCcontroller/ exposes the FastAPI controller, MCP transport, policy rails, and orchestration endpointsdata/ holds runtime artifacts, auth state, approvals, audit logs, and optional CLI cachesscripts/ contains local helpers for doctor, smoke tests, bridges, and release checks| Path | What It Contains |
| --- | --- |
| controller/ | controller API, MCP transport, tests, and packaging |
| browser-node/ | browser runtime and Playwright connection layer |
| examples/ | copy-paste flows and MCP client setup |
| integrations/langchain/ | LangChain, LangGraph, and CrewAI adapters |
| docs/ | architecture, deployment, hardening, and launch docs |
| scripts/ | doctor, smoke harnesses, stdio bridge, and auth helpers |
| ops/ | supporting service templates and operational assets |
| Command | Purpose |
| --- | --- |
| make help | list available repo commands |
| make lint | run Ruff checks on app, tests, and helper scripts |
| make test | run controller tests in Docker |
| make test-local | run controller tests on host Python 3.10+ |
| make doctor | run the local readiness smoke |
| make release-audit | run the fuller release-validation pass |
| make smoke-isolation | verify per-session Docker isolation |
| make smoke-reverse-ssh | verify reverse-SSH remote access |
| If You Want To... | Start Here |
| --- | --- |
| understand the system shape | docs/architecture.md |
| connect Claude Desktop or Cursor | docs/mcp-clients.md |
| run the curl-first examples | examples/README.md |
| deploy on a trusted host | docs/deployment.md |
| review production constraints | docs/production-hardening.md |
| inspect release history | CHANGELOG.md |
| see where the project is headed | ROADMAP.md |
If you want to help, start with:
CONTRIBUTING.mddocs/good-first-issues.mdNo comments yet. Be the first to share your thoughts!