MCP Launch Lens
Scores MCP servers for launch-readiness across trust, tool UX, docs, observability, marketplace fit, and partner narrative, and generates partner briefs and launch path comparisons.
README
MCP Launch Lens
A Manufact Cloud MCP App that turns an MCP server into a launch-readiness scorecard: trust, tool UX, docs, observability, marketplace fit, and partner narrative.
Built for the Manufact application as a live proof artifact: a deployed MCP URL, a visual widget, and a dashboard link that shows analytics, evals, logs, and observability.
Why this exists
Most MCP security tools answer: “is this risky?”
MCP Launch Lens answers a broader DevRel question:
Is this MCP integration ready to launch, partner around, and show to real users?
It builds on prior MCP infrastructure work:
@niraven/mcp-gateway— security-first MCP gateway, audit logging, approval gates, run reports.myelin-memory— MCP-native procedural memory for agents.
Tools
| Tool | Purpose | Widget |
|---|---|---|
assess-mcp-launch |
Scores an MCP app/server across launch-readiness dimensions | Yes |
generate-partner-brief |
Creates a DevRel/partnership launch brief | No |
compare-launch-paths |
Compares Manufact Cloud, ChatGPT Apps, Claude, and agent-client paths | No |
Local development
npm install
npm run build
npm run dev
Open the inspector at:
http://localhost:3000/inspector
Example call
{
"serverName": "mcp-gateway",
"description": "Security-first MCP gateway with audit logs and approval gates.",
"targetClients": ["Claude", "ChatGPT", "agent clients"],
"hasReadme": true,
"hasScreenshots": false,
"hasObservability": true,
"hasAuthStory": true,
"tools": [
{
"name": "scan-mcp-server",
"description": "Inspect MCP tools, permissions, and docs for launch risks.",
"sideEffect": "read",
"externalNetwork": false,
"hasTimeout": true,
"hasExamples": true
}
]
}
Live deployment
- MCP URL: https://keen-steel-bs1nz.run.mcp-use.com/mcp
- Manufact Cloud dashboard: https://manufact.com/cloud/org-bb5b108a-sifrx/servers/38b23d2a-f688-47b7-8425-59e143dcd6e1
- Inspector: https://inspector.manufact.com/inspector?autoConnect=https%3A%2F%2Fkeen-steel-bs1nz.run.mcp-use.com%2Fmcp
Deployment
Fast Manufact-managed deployment:
npx -y mcp-use@latest deploy --no-github -y --org org-bb5b108a-sifrx
GitHub-backed deployment after installing the mcp-use GitHub App:
npx -y mcp-use@latest deploy -y --org org-bb5b108a-sifrx
Application proof checklist
- Live MCP URL
- Manufact Cloud dashboard URL
- Widget screenshot
- Short walkthrough script
- Link to related GitHub proof:
mcp-gateway,myelin
See APPLICATION_PROOF.md for the verified proof package.
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.