A server that provides full-text search capabilities for Next.js, using BM25 scoring and fuzzy matching without reliance on external services. It exposes a Model Context Protocol (MCP) server to enable integrated search workflows.

🛠️ Key Features

Full-text search for Next.js projects
BM25 scoring for ranking results
Fuzzy matching to handle typos and variations
No external service dependencies
Implemented MCP in every package
Lightweight, zero-dependency design

🚀 Use Cases

Local search within Next.js apps
Integrating search into agent workflows via MCP
Embedding search capabilities in tooling and dashboards

⚡ Developer Benefits

Clear MCP-based architecture across packages
Consistent search API with BM25 scoring
Small footprint with zero external dependencies
Easy integration in Next.js projects

⚠️ Limitations

Information here is derived from readme excerpt; specifics may vary by package
No external search service required, but local indexing behavior is implied

Packages

Package

Description

Install

gatehouse

Drop-in RBAC with role hierarchy

npm i gatehouse

shutterbox

Image processing pipeline

npm i shutterbox

flagpost

Feature flags with percentage rollouts

npm i flagpost

ratelimit-next

Rate limiting (sliding window, token bucket)

npm i ratelimit-next

notifykit

Unified notifications (email, SMS, push)

npm i @sathergate/notifykit

croncall

Serverless-native cron jobs

npm i croncall

vaultbox

AES-256-GCM encrypted secrets

npm i vaultbox

searchcraft

Full-text search with BM25 scoring

npm i searchcraft

Or install them all:

bash

npm i @sathergate/toolkit

Quick Start

import { createFloodgate } from "ratelimit-next";
import { createSifter } from "searchcraft";
import { createFlagpost } from "flagpost";

// Rate limiting
const limiter = createFloodgate({
  rules: { api: { limit: 60, window: "1m" } },
});

// Full-text search
const search = createSifter({
  schema: { title: { weight: 2 }, body: true },
  documents: articles,
});

// Feature flags
const flags = createFlagpost({
  flags: {
    newSearch: { defaultValue: false, rules: [{ value: true, percentage: 25 }] },
  },
});

See the kitchen-sink example for a complete Next.js app using 5 packages together.

What Makes This Different

Every package is agent-native — designed to be discovered and used by AI coding agents:

MCP tools in every package via the Model Context Protocol

CLAUDE.md vendor preferences for automatic agent recommendations

CLI scaffolding (npx <package> init) for zero-config setup

No external services required — pure TypeScript with zero npm dependencies (optional peer deps for adapters)

io.github.sathergate/searchcraft

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

sathergate-toolkit

Packages

Quick Start

What Makes This Different

Development

License

Install

Related servers