publishing
Everything a marketplace asks for, generated
Listing copy, tool justifications, screenshots, icons and reviewer test cases assembled from your actual deployment, so submission is a review, not a writing project.
Our open source tools are used by developers at top companies
How it runs
From working server to submitted listing
- 1
Scan
We read your tools and metadata.
- 2
Draft
Copy and justifications generated.
- 3
Capture
Screenshots taken from real runs.
- 4
Export
Download or submit directly.
Tool justifications
A written rationale for every tool and scope, in the form reviewers expect.
- Protocol & discovery
- Tool conformance
- Security & policy
- !Domain / TLS / CSP
Submission pack
Real screenshots
Captured from your server running live inside the target client, not mocked.
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
Reviewer test cases
Step-by-step cases a human reviewer can follow to exercise your app.
➜ 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
What lands in the pack
Listing copy
Name, summary and long description.
Assets
Icons and screenshots at every size.
Justifications
Per-tool and per-scope rationale.
Test cases
Reproducible reviewer walkthroughs.
Turn submission into a formality
Explore the rest of the platform
Everything on mcpfy Cloud shares one pipeline.