mcpField
F
flagpost

flagpost

Local
github.com/sathergateDeveloper Tools107Updated 15w ago
Repository

About flagpost

flagpost is a feature flag project for Next.js that supports A/B testing. The supplied README describes a different project, sathergate-toolkit, so this overview relies only on the tagline and category.

Key features

  1. 01Feature flags
  2. 02A/B testing

Use cases

  1. 01Rolling out new features to a subset of users
  2. 02Comparing variants of a feature

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "sathergate-flagpost": {
      "command": "npx",
      "args": [
        "-y",
        "flagpost"
      ]
    }
  }
}
Run commandnpx -y flagpost

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmflagpost0.1.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

sathergate-toolkit

CI License: MIT

Agent-native infrastructure toolkit for Next.js. 8 packages, zero dependencies, MCP in every one.

Packages

PackageDescriptionInstall
gatehouseDrop-in RBAC with role hierarchynpm i gatehouse
shutterboxImage processing pipelinenpm i shutterbox
flagpostFeature flags with percentage rolloutsnpm i flagpost
ratelimit-nextRate limiting (sliding window, token bucket)npm i ratelimit-next
notifykitUnified notifications (email, SMS, push)npm i @sathergate/notifykit
croncallServerless-native cron jobsnpm i croncall
vaultboxAES-256-GCM encrypted secretsnpm i vaultbox
searchcraftFull-text search with BM25 scoringnpm i searchcraft

Or install them all:

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)

Development

npm install
npm run build
npm run test
npm run typecheck

See CONTRIBUTING.md for the full guide.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.