Developer · Remote MCP server

Preflight

Check if your MCP server is ready to publish on the MCP Registry, Smithery, or npm.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.evanfollis/preflight
Version
0.1.1
Status
Active
Category
developer
Transport
Streamable HTTP
Published
2026-07-26
Updated
2026-07-26
Publisher
evanfollis (GitHub)
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/evanfollis) · how
Repository
github.com/evanfollis/skillfoundry-products
Source
Registry API entry

Remote endpoints

TransportURLHeaders declared
Streamable HTTPhttps://skillfoundry.synaplex.ai/products/preflight/mcp/None

Live check

This directory connected to each remote endpoint and asked for its list of tools. The check connects and lists tools only; it doesn't run tools, sign in or test security.

Reachable
Yes (HTTP 200)
Handshake
preflight 0.1.1 · protocol 2025-11-25
Tools discovered
1: check_publish_readiness
Checked on
2026-10-05

How the live check works

How to connect Preflight

Preflight is a remote MCP server: there is nothing to install. Its endpoint is https://skillfoundry.synaplex.ai/products/preflight/mcp/, served over Streamable HTTP. In an assistant that accepts remote MCP servers (often under a setting named connectors, integrations or tools), add a new server and give it this URL; in a client configured by file, add it as a remote (HTTP) server with the same URL.

No headers are declared in the registry entry. If the server needs you to sign in, a client that supports MCP authorization opens the service's own sign-in page when it first connects.

Derived from the registry entry; the live check above only shows whether the endpoint answered. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More developer servers

All 5,152 →
ServerRunsEndpoint or package
Pqs MCP ServerPQS scores any prompt before the model runs. 8 dimensions. 5 frameworks. Pre-flight, not post-hoc.Remote & Local · HTTP, stdioLive check: ✓ handshakepromptqualityscore.com
Pramana MCPRead your recorded AI agent runs, and what changed when you swapped a model or prompt.Local · stdioPyPI: pramana-mcp
Predictive DebuggerPredicts where JavaScript and TypeScript code will fail at runtime, for coding agents.Local · stdionpm: predictive-debugger
PrefabList, create and deploy your Prefab project templates from any MCP agent.Local · stdionpm: prefab-mcp
PreflightNew Relic MCP server for observing AI coding assistants (Claude Code, Cursor, Copilot, etc.)Local · stdionpm: @newrelic/preflight
Presend dependency checksCheck an npm/PyPI package before an AI agent installs it: 5 focused supply-chain tools.Remote · HTTPLive check: ✓ handshakepresend.pages.dev
Presend MCP ServerBefore an AI agent installs an npm/PyPI package: typosquat, vulnerability and existence checks.Remote · HTTPLive check: ✓ handshakepresend.pages.dev
pRESTStdio MCP adapter bridging AI clients to pREST’s HTTP /_mcp endpoint for PostgreSQL APIs.Local · stdioOCI image (Docker): ghcr.io/prest/prest-mcp-adapter:0.1.3