npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@viyrockan/fedlearn-mcp

v0.1.2

Published

MCP integration for FedLearn local continual learning (Cursor, Claude Desktop, AntiGravity)

Downloads

20

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

viyrockanviyrockan

Keywords

Readme

@viyrockan/fedlearn-mcp

MCP server that bridges Cursor, Claude Desktop, and AntiGravity MCP tool calls into FedLearn local continual learning.

Modes

Best-effort mode

Use this package directly and let the chat client decide tool usage. Tool flow should be: pre_turn -> get_personalization_context -> answer -> learn_from_turn.

Guaranteed mode

Use this package with @viyrockan/fedlearn-orchestrator to enforce the full flow every exchange from host code.

It uses an explicit 4-step loop:

  1. pre_turn(...) for immediate micro-progress update,
  2. get_personalization_context(...) before answering,
  3. answer conditioned on returned context,
  4. learn_from_turn(...) after answering.

Inputs

  • pre_turn(userId?, conversationId, latestInput?)
  • get_personalization_context(userId?, conversationId, latestInput?)
  • learn_from_turn(userId, conversationId, input, output, turnId?)

Outputs

  • pre_turn: immediate micro-progress summary so percentage can move each exchange.
  • get_personalization_context: moderate-token style context (tone/format/detail/confidence + fallback note).
  • learn_from_turn: short applied-now summary including sessionsRetained, personalization %, budget remaining, and rank label.
    • duplicate turnId calls are ignored for retry-safe idempotency.

Local persistence

FedLearn persists adapter state using the existing fedlearn-core Node persistence:

  • by default: a ./.fedlearn-local-adapters.json file relative to the process working directory
  • optionally override via FEDLEARN_LOCAL_STORE

Supported MCP clients

This repo currently targets Cursor, Claude Desktop, and AntiGravity. Configure your client to run this server as a stdio tool process and call: pre_turn then get_personalization_context before drafting, and learn_from_turn after final answer.

For deterministic "every turn updates" behavior, route all turns through @viyrockan/fedlearn-orchestrator in your host integration.

Token budget note

This package intentionally returns compact context to keep overhead moderate. If confidence is low, context instructs neutral fallback instead of forcing aggressive style steering.