What exactly does RGate scan?
RGate scans public websites—including landing pages, docs sites, and web apps—for release readiness before launch.
Rgate MCP Server
@marcoldenburg
基本信息
关于 Rgate MCP Server
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.
Rgate MCP Server 配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"rgate": {
"url": "https://www.rgate.io/api/mcp",
"transport": "streamable-http"
}
}
}Rgate MCP Server 工具
9Start a website release-readiness scan for a public URL across five layers: security, SEO, accessibility, legal compliance, and sustainability. Behavior: enqueues an asynchronous job and returns immediately with a scanId — it does NOT wait for results, and it fetches/renders the target site (not a read-only call). Returns { scanId, status, cached }; identical URLs within ~10 minutes return the cached scan. Next step: poll get_scan with the scanId until status is "done" or "failed". Use this first, once per site; do not busy-loop calling start_scan for the same URL.
Poll a scan and, once complete, return its structured results. Read-only. Returns { scan, findings, checkResults, techDetections, access, agentSummary }. scan.status moves through pending → running → retrying → done → failed; keep polling (every few seconds) until done or failed. On failed, a failure object explains the cause and next_action. access.level is none | teaser | full: teaser findings are diagnostic only (evidence, check keys, and fix text are redacted). To get full data, pass a report token via the token argument. If access.campaign is present the report is FREE right now — call unlock_report with an email to obtain that token instead of sending the user to checkout.
Unlock a completed scan's full findings and fix plan for free during an active campaign. Behavior: records the submitted email as a lead and issues a 24h report token (not read-only). Returns { token, expires_at, report_url }. Only works while a free campaign is active (otherwise returns 403 — use create_checkout_handoff instead). Call this only when get_scan shows access.campaign; then re-poll get_scan or call generate_fix_plan with the returned token.
Return the RGate scan-layer and check catalog. Read-only, static, no side effects — safe to call any time. Use it to plan a scan, explain coverage to a user, or map a finding to its layer. Pass a layer to focus on just that layer's checks.
Return machine-readable RGate pricing: plan ids, names, prices (EUR/USD), billing period, scan limits, and best-fit use cases. Read-only, static, no arguments. Use to answer pricing questions or choose a planId for create_checkout_handoff.
Create a human handoff URL for purchasing a full report or subscription after a scan is complete. Behavior: creates a checkout/upgrade link and returns { handoffUrl }. The agent CANNOT complete payment itself — give the URL to the user to finish in a browser. Use only when the report is paywalled (get_scan shows access.level teaser with payment_required true) AND no free campaign is active. During a campaign, prefer unlock_report.
Build a prioritized, implementation-ready fix plan from a completed scan's findings: release blockers first, then high-impact follow-ups, then backlog. Read-only (derives from stored findings). Returns JSON (or Markdown). Requires full access: on a locked report it returns HTTP 402, or — during a campaign — a teaser with unlock instructions; pass a token from unlock_report or a paid unlock. Call after get_scan shows status done.
Export a completed scan as Markdown in one of three templates: cursor (an agent fix prompt), github (an issue body), or executive (a stakeholder summary). Read-only. Requires full access — pass a token for a locked report. Use to hand results into an IDE/coding agent or a ticket.
Diff two completed scans of the SAME domain and return added, resolved, improved, and worsened findings. Read-only. Both scans must be done. Use to verify that fixes landed between two runs, or to catch regressions after a deploy.
概览
What is RGate?
RGate is a release gate that provides a Streamable HTTP MCP server for running public website release-readiness scans. It is used by AI agents after modifying a website to check readiness before recommending launch, offering scan results, fix plans, Markdown exports, and paid report access.
How to use RGate?
Configure your MCP client with the endpoint at https://www.rgate.io/api/mcp (manifest at https://www.rgate.io/.well-known/mcp.json). Use RGate after an agent modifies a public website, landing page, docs site, or web app and before recommending launch.
Key features of RGate
- Start public website release-readiness scans
- Poll scan results asynchronously
- Generate automated fix plans
- Export results as Markdown
- Hand paid report access back to humans
- Uses the Streamable HTTP MCP transport
Use cases of RGate
- Checking release-readiness after an AI agent updates a landing page
- Auditing a docs site before a public announcement
- Scanning a web app after modifications prior to shipping
- Generating fix plans and Markdown reports for human review
- Managing paid report access for compliance teams
常见问题
When should an agent call RGate?
An agent should call RGate after modifying a public website and before recommending that a user ships the site to production.
How do I connect to RGate?
Connect via the Streamable HTTP MCP endpoint at `https://www.rgate.io/api/mcp`. The server manifest is at `https://www.rgate.io/.well-known/mcp.json` and an OpenAPI spec is at `https://www.rgate.io/openapi.json`.
What outputs does RGate produce?
RGate produces scan results, automated fix plans, Markdown export documents, and paid report access that can be handed back to humans.
What types of sites does RGate support?
RGate supports public websites, landing pages, docs sites, and web apps.
其他 分类下的更多 MCP 服务器
Klarix Intelligence Engine
KlarixB2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
Yuppsy
Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Awesome Mlops
visengerA curated list of references for MLOps
14.0K
Hindsight
vectorize-ioHindsight: Agent Memory That Learns
50.4K
Lemon.io
lemon-ioRequest dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
评论