publishing
Know you're ready before you submit
Six categories of checks mapped to marketplace requirements, each failure with fix guidance and an autofix flow, plus live end-to-end runs inside the real clients.
Our open source tools are used by developers at top companies
How it runs
From first build to an accepted listing
- 1
Audit
Run all six check categories.
- 2
Fix
Apply guided fixes or autofix.
- 3
Verify
End-to-end runs in real clients.
- 4
Submit
Ship with a generated submission pack.
Six check categories
Protocol and discovery, tool conformance, security and policy, metadata, domain/TLS/CSP, and assets.
- Protocol & discovery
- Tool conformance
- Security & policy
- !Domain / TLS / CSP
Submission pack
End-to-end verification
Your server runs live inside ChatGPT and Claude to confirm tool calls and widget rendering.
San Francisco, CA
72°F
Partly cloudy · H 74° L 58°
→ tools/call
{
"name": "display_weather",
"arguments": { "city": "San Francisco" }
}← result20041ms
{ "content": [{ "type": "resource" }] }GPT-5.2
18/18
Claude
18/18
Gemini
17/18
Submission pack
Listing copy, tool justifications, screenshots and reviewer test cases, generated for you.
➜ npx create-mcpfy-app
✓ tools/chart-sales.ts
✓ widgets/Chart.tsx
✓ mcpfy.config.ts
➜ mcpfy dev
ready on :4141 · 6 tools registered
tools/chart-sales.ts
export const chartSales = tool({
name: "chart_sales",
input: z.object({ period: z.string() }),
});In the box
Everything reviewers look for
Protocol & discovery
Correct handshakes and capability lists.
Tool conformance
Schemas that match real behaviour.
Security & policy
Scopes, consent and data handling.
Assets & metadata
Icons, copy and configuration.
Get through review on the first attempt
Explore the rest of the platform
Everything on mcpfy Cloud shares one pipeline.