reshapr

Name: reshapr
Author: reshaprio

by reshaprio

Verified

The open source, no-code MCP Server for AI-Native API Access

110stars

20forks

Java

Added 6/3/2026

Installation

# Add to your Claude Code skills
git clone https://github.com/reshaprio/reshapr

Getting Started

Guides for using ai agents skills like reshapr.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 6/3/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-06-03T08:55:40.675Z",
  "npmAuditRan": true,
  "pipAuditRan": true
}

README.md

Frequently Asked Questions

What is reshapr?

reshapr is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by reshaprio. The open source, no-code MCP Server for AI-Native API Access. It has 110 GitHub stars.

Is reshapr safe to use?

Yes. reshapr passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install reshapr?

Clone the repository with "git clone https://github.com/reshaprio/reshapr" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is reshapr written in?

reshapr is primarily written in Java. It is open-source under reshaprio on GitHub, so you can review or fork the full source.

Are there alternatives to reshapr?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh reshapr against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

ralphy solo

Welcome to reShapr 🚀

Website | About | Docs | Blog | Community

✨ What is reShapr?

reShapr is the open source, no-code MCP Server for AI-Native API Access. It bridges the gap between traditional REST/GraphQL/gRPC services and LLMs by transforming complex services into discoverable, optimized MCP tools.

[!IMPORTANT] To get involved with our community, please familiarize yourself with the project's Code of Conduct.

🧠 Solving the "Context Window" Problem

One of the biggest hurdles in building AI agents is Context Overload. Sending massive JSON responses to an LLM wastes tokens and degrades performance.

reShapr introduces Context Control

🌟 Key Features

AI-Native Transformation: Auto-transform API services into LLM-friendly tools.
Context Control: Filter and slim down payloads before they reach the LLM.
Multi-Protocol: REST, GraphQL, and gRPC support.
No-Code: Configure and deploy in minutes.

📖 Full Documentation | Discord Community

Quick Start

Install the CLI

npm install -g @reshapr/reshapr-cli

Choose your platform

You have two simple options:

Use the https://try.reshapr.io/ to try out the platform. Follow our detailed Try reShapr online guide.
Run the platform locally using containers and Docker runtime. Follow the next section for details.

Run the platform locally

Assuming you have Docker installed, you can run the platform locally with the following command:

reshapr run

You should see a message like this:

ℹ️  Resolved 'latest' to release '0.0.14'.
ℹ️  Downloading compose file from https://raw.githubusercontent.com/reshaprio/reshapr/refs/tags/0.0.14/install/docker-compose-all-in-one.yml...
✅ Compose file saved to /Users/<you>/.reshapr/docker-compose-0.0.14.yml
ℹ️  Starting Reshapr containers (release: 0.0.14)...
✅ Reshapr containers started successfully.

Connect to the control plane at http://localhost:5555 with default credentials (admin/password):

reshapr login -s http://localhost:5555 -u admin -p password

Import an OpenAPI file:

reshapr import -u https://raw.githubusercontent.com/open-meteo/open-meteo/refs/heads/main/openapi.yml \
  --backendEndpoint https://api.open-meteo.com

You now have a fully functional MCP Server powered by reShapr at http://localhost:7777/mcp/reshapr/Open-Meteo+APIs/1.0 🎉

You can try it out using an MCP client, explore the CLI and more features!

Contributing

We ❤️ contributors! Reshapr is an open community, and we welcome contributions of all kinds — not just code. Every contribution matters and helps make Reshapr better for everyone:

🐛 Report bugs or submit support requests via GitHub Issues
📖 Improve documentation — fix a typo, clarify a guide, or write a new tutorial
🧪 Write tests to increase coverage and reliability
🎥 Create demos or share your use cases with the community
💻 Submit code — bug fixes, features, or refactors are all welcome
💬 Share testimonials — tell us how you use Reshapr and help spread the word

📋 Before contributing, please read our Contributing Guide to learn about our development workflow, coding conventions, and how to submit your changes.

Come say hi on our Discord server — whether you have questions, ideas, or just want to chat with the community. We'd love to hear from you! 🚀

Support the project! 🌟

If you think reShapr is useful for the AI ecosystem, give us a star on our main repository! It helps us get more visibility and keep the project growing.