reShapr
OfficialSupports transforming GraphQL services into MCP tools, enabling AI-native access to GraphQL APIs with context control.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Welcome to reShapr ๐
Website | About | Docs | Blog | Community
โจ What is reShapr?
reShapr is the open source runtime that turns your existing APIs AI-Native, without rebuilding them. It bridges the gap between traditional REST/GraphQL/gRPC services and LLMs by transforming them into governed, discoverable, context-optimized MCP tools.
To get involved with our community, please familiarize yourself with the project'sCode of Conduct.
๐ง 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
Related MCP server: rest2mcp
๐ 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.
Zero Rewrite: Import an existing contract and get working MCP tools in minutes, with no bespoke MCP server per API.
๐ Full Documentation | Discord Community
Quick Start
Install the CLI
(Requires Node.js installed)
npm install -g @reshapr/reshapr-cliChoose your platform
Choose how to get started:
Try it online: Use try.reshapr.io for a fully managed sandbox. Follow our Try reShapr online guide.
Run it locally (End-User): See the section below to spin up the latest published release.
Contribute code / launch the Web UI (Developer): Head to install/README.md to run the
docker-composestack โ it uses:nightlydevelopment builds.
Run the platform locally
Assuming you have Docker installed, you can run the platform locally with the following command:
reshapr runYou should see a message like this:
โน๏ธ Resolved 'latest' to release '1.0.0'.
โน๏ธ Downloading compose file from https://raw.githubusercontent.com/reshaprio/reshapr/refs/tags/1.0.0/install/docker-compose-all-in-one.yml...
โ
Compose file saved to /Users/<you>/.reshapr/docker-compose-1.0.0.yml
โน๏ธ Starting Reshapr containers (release: 1.0.0)...
โ
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 passwordImport an OpenAPI file:
reshapr import -u https://raw.githubusercontent.com/open-meteo/open-meteo/refs/heads/main/openapi/forecast.yml \
--backendEndpoint https://api.open-meteo.comYou now have a fully functional MCP Server powered by reShapr at http://localhost:7777/mcp/reshapr/open-meteo-weather-forecast-api-1-0-default ๐
You can try it out using an MCP client, explore the CLI and more features!
Build Status
The current development version is 1.0.1-SNAPSHOT.
Signature, Provenance, SBOM
Sonarcloud Quality metrics
LFX Insights
OpenSSF best practices
Contributing
We โค๏ธ contributors! Reshapr is an open community, and we welcome contributions of all kinds โ not just code. Every contribution matters and helps make Reshapr better for everyone:
๐ Report bugs or submit support requests via GitHub Issues
๐ Improve documentation โ fix a typo, clarify a guide, or write a new tutorial
๐งช Write tests to increase coverage and reliability
๐ฅ Create demos or share your use cases with the community
๐ป Submit code โ bug fixes, features, or refactors are all welcome
๐ฌ Share testimonials โ tell us how you use Reshapr and help spread the word
๐ 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 โ whether you have questions, ideas, or just want to chat with the community. We'd love to hear from you! ๐
Support the project! ๐
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.
Thanks!
This server cannot be deployed
Maintenance
Related MCP Connectors
Discover and call 10,000+ production APIs from one MCP server. Pay-per-call billing for AI agents.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
Governed app access for AI agents: 1,000+ apps & 12,000+ tools via Code Mode MCP.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceTurns any OpenAPI/Swagger API into MCP tools, enabling AI assistants to call REST API endpoints directly.25 PyPI2MIT
- FlicenseNot gradedqualityDmaintenanceExposes any REST API as MCP tools, enabling AI agents to discover and call existing HTTP endpoints without modifying the original API.-
- AlicenseNot gradedqualityCmaintenanceFederates MCP, A2A, and REST/gRPC APIs with centralized governance, discovery, and observability, optimizing agent and tool calling with plugin support.Apache 2.0
- FlicenseNot gradedqualityBmaintenanceEnables turning existing REST APIs into governed, agent-callable MCP servers by analyzing OpenAPI schemas, generating tool definitions, and gating releases behind automated evals.-