Update Night MCP
Provides tools for AI assistants to search and explore the Update Night catalog of AI development tools, including agent frameworks, skills, and MCP servers. Enables querying entries by category, fetching detailed entries, and browsing recent news.
README
Update Night MCP
MCP server for the Update Night catalog. Gives AI assistants tools to search and explore AI dev tools, agent frameworks, skills, and MCP servers.
Install
Option 1 — cargo-binstall (pre-built binary, fastest)
cargo binstall updatenight-mcp
Installs the pre-built binary for your platform. Get cargo-binstall from cargo-bins/cargo-binstall if you don't have it.
Option 2 — Download binary
Go to Releases and grab the archive for your platform:
| Platform | File |
|---|---|
| macOS Apple Silicon | updatenight-mcp-aarch64-apple-darwin.tar.gz |
| macOS Intel | updatenight-mcp-x86_64-apple-darwin.tar.gz |
| Linux x86_64 | updatenight-mcp-x86_64-unknown-linux-gnu.tar.gz |
| Linux ARM64 | updatenight-mcp-aarch64-unknown-linux-gnu.tar.gz |
| Windows x86_64 | updatenight-mcp-x86_64-pc-windows-msvc.zip |
macOS / Linux:
# Replace <target> with your platform (e.g. aarch64-apple-darwin)
curl -fsSL https://github.com/amajorai/updatenight-mcp/releases/latest/download/updatenight-mcp-<target>.tar.gz \
| tar xz -C /tmp
sudo mv /tmp/updatenight-mcp /usr/local/bin/updatenight-mcp
Windows (PowerShell):
# Run as Administrator
$target = "x86_64-pc-windows-msvc"
$url = "https://github.com/amajorai/updatenight-mcp/releases/latest/download/updatenight-mcp-$target.zip"
Invoke-WebRequest $url -OutFile "$env:TEMP\updatenight-mcp.zip"
Expand-Archive "$env:TEMP\updatenight-mcp.zip" -DestinationPath "$env:TEMP\updatenight-mcp-bin"
Move-Item "$env:TEMP\updatenight-mcp-bin\updatenight-mcp.exe" "C:\Windows\System32\updatenight-mcp.exe"
Option 3 — Build from source
git clone https://github.com/amajorai/updatenight-mcp
cd updatenight-mcp
cargo build --release
# binary at target/release/updatenight-mcp (or .exe on Windows)
sudo mv target/release/updatenight-mcp /usr/local/bin/updatenight-mcp
Updating
Re-run whichever install method you used. For cargo-binstall:
cargo binstall updatenight-mcp
Tools
search — search the catalog by query string. Optionally filter by kind (tool, skill, mcp) and set a result limit. Returns entries with name, tagline, pricing, and install snippets.
get_entry — fetch a single catalog entry by kind and slug. Returns full details including description, pricing, install snippet, and homepage URL.
list_by_category — list entries by kind and category slug (e.g. agent-framework, llm, rag, vector-db). Returns entries sorted by publish date.
list_news — fetch recent news items from the Update Night news timeline. Accepts a days parameter (default 7). Returns titles, summaries, sources, and timestamps.
Authentication
On first run the server starts a device authorization flow, prints a verification URL and code to stderr, and opens your browser. Once approved, the token is saved and subsequent runs start immediately.
Token location: ~/.config/updatenight/mcp-config.json (Linux/macOS) or %APPDATA%\updatenight\mcp-config.json (Windows).
Installation by host
Replace /usr/local/bin/updatenight-mcp with the actual path to your binary in all configs below.
Claude Desktop
Config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/claude-desktop/claude_desktop_config.json
{
"mcpServers": {
"updatenight": {
"command": "/usr/local/bin/updatenight-mcp"
}
}
}
Quit and relaunch Claude Desktop after editing.
Claude Code
claude mcp add updatenight /usr/local/bin/updatenight-mcp
To add it at project scope (committed to .mcp.json for team sharing):
claude mcp add --scope project updatenight /usr/local/bin/updatenight-mcp
Cursor
Config file:
- Project:
.cursor/mcp.json - Global:
~/.cursor/mcp.json
{
"mcpServers": {
"updatenight": {
"command": "/usr/local/bin/updatenight-mcp"
}
}
}
Quit and reopen Cursor after editing.
Windsurf
Config file:
- macOS/Linux:
~/.codeium/windsurf/mcp_config.json - Windows:
%USERPROFILE%\.codeium\windsurf\mcp_config.json
{
"mcpServers": {
"updatenight": {
"command": "/usr/local/bin/updatenight-mcp"
}
}
}
VS Code (GitHub Copilot)
Config file: .vscode/mcp.json in your project root (commit to share with your team).
Note: VS Code uses servers not mcpServers, and requires an explicit "type" field.
{
"servers": {
"updatenight": {
"type": "stdio",
"command": "/usr/local/bin/updatenight-mcp"
}
}
}
MCP tools are only available in Agent mode in VS Code Copilot Chat.
Cline (VS Code extension)
Open the Cline panel, click the MCP Servers icon, go to the Configure tab, and click "Configure MCP Servers". Add to the JSON that opens:
{
"mcpServers": {
"updatenight": {
"command": "/usr/local/bin/updatenight-mcp"
}
}
}
Continue.dev
Config file: ~/.continue/config.yaml (macOS/Linux) or %USERPROFILE%\.continue\config.yaml (Windows).
mcpServers:
- name: Update Night
command: /usr/local/bin/updatenight-mcp
type: stdio
Or drop a JSON file at .continue/mcpServers/updatenight.json in your project:
{
"mcpServers": {
"updatenight": {
"command": "/usr/local/bin/updatenight-mcp"
}
}
}
Zed
Config file:
- macOS:
~/.zed/settings.json - Linux:
~/.config/zed/settings.json - Windows:
%APPDATA%\Zed\settings.json - Project:
.zed/settings.json
Note: Zed uses context_servers not mcpServers.
{
"context_servers": {
"updatenight": {
"command": "/usr/local/bin/updatenight-mcp",
"args": []
}
}
}
Amazon Q Developer
Config file:
- Global:
~/.aws/amazonq/mcp.json - Project:
.amazonq/mcp.json
{
"mcpServers": {
"updatenight": {
"command": "/usr/local/bin/updatenight-mcp"
}
}
}
Gemini CLI
Config file:
- Global:
~/.gemini/settings.json - Project:
.gemini/settings.json
{
"mcpServers": {
"updatenight": {
"command": "/usr/local/bin/updatenight-mcp"
}
}
}
OpenAI Codex CLI
Config file: ~/.codex/config.toml (global) or .codex/config.toml (project).
Note: Codex uses TOML, not JSON.
[mcp_servers.updatenight]
command = "/usr/local/bin/updatenight-mcp"
args = []
Raycast
Open Raycast, run "Manage MCP Servers", press Cmd+N to add a new server, or open the config file directly at ~/Library/Application Support/com.raycast.macos/extensions/EvanZhouDev.mcp/mcp.json:
{
"mcpServers": {
"updatenight": {
"command": "/usr/local/bin/updatenight-mcp"
}
}
}
Configuration
UPDATENIGHT_API_URL — API host to connect to. Defaults to https://server.updatenight.com if not set.
For local development, set it to your local server (port 3000 by default). You can do this in the .env file next to the binary, or pass it via your host's MCP env config:
{
"mcpServers": {
"updatenight": {
"command": "/usr/local/bin/updatenight-mcp",
"env": {
"UPDATENIGHT_API_URL": "http://localhost:3000"
}
}
}
}
The binary also loads a .env file from the working directory at startup if one is present.
Related
- Update Night CLI — terminal UI for browsing the catalog
- Update Night Skill — Claude Code skill for browsing the catalog from any AI agent
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.