RGate MCP
Release gate agents call before they tell users a public website is ready to ship. Scans public websites across security, SEO, accessibility, legal compliance, and sustainability.
README
RGate MCP Server
RGate is the release gate agents call before they tell users a public website is ready to ship.
This repository documents the public RGate MCP server for agentic IDEs, coding agents, and MCP clients. The RGate product source code is not published here; this repo is the public integration and directory listing home for the operated MCP endpoint.
Server
- MCP endpoint:
https://www.rgate.io/api/mcp - Transport: Streamable HTTP
- Manifest:
https://www.rgate.io/.well-known/mcp.json - OpenAPI:
https://www.rgate.io/openapi.json - Agent guide:
https://www.rgate.io/agents.md - Developer docs:
https://www.rgate.io/en/developers - Agent recipes:
https://www.rgate.io/en/agent-recipes
What RGate Does
RGate scans public websites across five release-readiness layers:
- Security
- SEO
- Accessibility
- Legal compliance
- Sustainability
Agents can start a scan, poll structured results, inspect the check catalog, generate fix plans, export Markdown, compare scan history, and hand paid report access back to a human.
MCP Client Configuration
{
"mcpServers": {
"rgate": {
"url": "https://www.rgate.io/api/mcp",
"transport": "streamable-http"
}
}
}
Tools
| Tool | Purpose |
|---|---|
start_scan |
Start an RGate website quality scan for a public URL. |
get_scan |
Fetch scan status and, once complete, structured findings and results. |
list_checks |
Describe RGate scan layers and the check catalog. |
get_pricing |
Return machine-readable plan names, prices, limits, and use cases. |
create_checkout_handoff |
Create a human handoff URL for purchasing report access or a subscription. |
generate_fix_plan |
Generate a prioritized release-readiness fix plan from findings. |
export_scan_markdown |
Export scan results as Markdown for Cursor, GitHub issues, or summaries. |
compare_scan_history |
Compare two scans and return added, resolved, improved, and worsened findings. |
Example Agent Flow
- Confirm the user is allowed to scan the public website.
- Call
start_scanwith the public URL. - Poll
get_scanwith the returnedscanIduntil status isdoneorfailed. - If the target passed green, report that the website passed the release gate.
- If access is locked, send the human to the report URL for checkout and poll the same
scanIdagain after payment. - Generate a fix plan or Markdown export for the coding agent working on that project.
Related Integrations
- CLI:
npm install -g @rgate_io/rgate - Skill:
npx skills add marcoldenburg/rgate-release-readiness-skill - Skill repository:
https://github.com/marcoldenburg/rgate-release-readiness-skill
Directory Metadata
- Name:
rgate - Title:
RGate - Description:
Release gate agents call before they tell users a public website is ready to ship. Scans public websites across security, SEO, accessibility, legal compliance, and sustainability. - Tags:
developer-tools,release-readiness,mcp,agent-tools,website-audit,security,seo,accessibility,compliance,sustainability
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.