AnythingMCP: AI-Empowered Gateway for Custom Claude, ChatGPT, Gemini Connectors
This repository profile is provided by osrepos.com, an open source repository discovery platform.

Summary
AnythingMCP is a self-hosted, open-source AI-empowered gateway that transforms existing APIs, databases, and MCP servers into custom connectors for leading AI models like Claude, ChatGPT, and Gemini. It enables no-code integration of REST, SOAP, GraphQL, and SQL sources into the Model Context Protocol, featuring robust authentication, access control, and audit logging. The platform also includes over 175 pre-built adapters for common services, simplifying complex integrations.
Repository Information
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
AnythingMCP is a powerful, self-hosted, and open-source AI-empowered gateway designed to bridge your existing systems with modern AI agents. It acts as a Model Context Protocol (MCP) server, allowing you to turn any REST, SOAP, WSDL, GraphQL API, or SQL/NoSQL database into custom connectors for AI models such as Claude, ChatGPT, Gemini, Copilot, and Cursor. This platform eliminates the need for custom code, providing a no-code solution to integrate your business data and services directly into AI workflows.
Beyond simple conversion, AnythingMCP is smart. It builds a per-workspace Knowledge Graph of how your connectors' data relates, enabling AI agents to chain tools correctly across systems. It also captures reusable AI skills from actual tool usage, guiding agents effectively. With over 175 pre-built adapters, it offers quick integration for many popular services, from logistics to ERP systems.
Find out more on the official AnythingMCP GitHub repository.
Installation
Getting AnythingMCP up and running is designed to be quick and straightforward, especially with Docker.
Get started in 60 seconds:
To begin, ensure you have Docker 24+, bash, and openssl installed. On macOS, start Docker Desktop first.
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && ./setup.sh
# When setup finishes, open http://localhost:3000 and register
# the first user, they automatically become the admin.
The interactive setup.sh script handles deployment mode, domain, HTTPS (via Caddy), secrets, MCP auth, and optional SMTP/Redis configuration.
Default URLs after setup:
- Web UI:
http://localhost:3000 - MCP endpoint:
http://localhost:4000/mcp - Swagger docs:
http://localhost:4000/api/docs
One-click deploy options are also available:
For manual setup, copy .env.example to .env and run docker compose up -d. Refer to the Deployment Guide for details.
Examples
AnythingMCP offers a rich set of features and pre-configured connectors to integrate diverse systems with AI agents.
Key Features:
- 5 Connector Types: REST, SOAP, GraphQL, Database (PostgreSQL, MySQL, MariaDB, MSSQL, Oracle, MongoDB, SQLite), and MCP-to-MCP bridge.
- 6 Import Formats: OpenAPI/Swagger, Postman, cURL, WSDL, GraphQL introspection, and custom JSON.
- 175+ Pre-built Adapters: Ready-to-use integrations for logistics, ERP, HR, e-commerce, payments, and public data. Examples include Deutsche Bahn, weclapp ERP, Etsy, Shopware, DHL, and Sendcloud.
- Visual Tool Editor: Map parameters, rename, and describe tools for AI consumption.
- Dynamic MCP Server: Tools are registered at runtime without requiring a restart.
- Knowledge Graph & AI Skills: A per-workspace, PII-safe map of data relationships, served to the agent via an MCP tool, plus reusable AI skills.
- Full Authentication: OAuth2, Bearer, API Key, Basic, WS-Security, client certificates, LOGIN_TOKEN, and OAuth 1.0a handshakes.
- Audit Logging: Every tool call is logged with input, output, duration, and status.
- Roles & Access Control: Tool-level whitelisting per custom role, per-user MCP API keys.
Typical Use Cases:
- Search train schedules and live delays with Deutsche Bahn.
- Communicate with your ERP from Claude, such as weclapp or Xentral.
- Track parcels with AI using DHL or GLS integrations.
- Validate invoices with VIES VAT or Handelsregister.
- Allow agents to query production databases safely.
- Bridge legacy SOAP services to modern AI platforms.
- Import a Postman collection and instantly get MCP tools.
Why Use AnythingMCP
AI clients communicate using the Model Context Protocol, but your existing systems speak REST, SOAP, GraphQL, and SQL. Developing and maintaining a custom MCP server for each system, complete with authentication, audit logs, and access control, can be a time-consuming and complex task. AnythingMCP provides the essential no-code layer to bridge this gap.
It offers a comprehensive solution by providing:
- Seamless Conversion: Transforms REST, SOAP, GraphQL, and database endpoints into MCP tools effortlessly.
- Extensive Adapter Library: Access to over 175 pre-built adapters, allowing one-click installation for common services.
- Self-Hosted Security: Runs on your infrastructure, ensuring your credentials remain secure and under your control, with AES-256-GCM encryption at rest.
- Built-in Enterprise Features: Includes robust OAuth2, comprehensive audit logging, and role-based access control (RBAC) out of the box, eliminating the need for custom development.
- Universal Compatibility: Build your connector once and use it simultaneously across Claude, ChatGPT, Gemini, Copilot, and Cursor, maximizing your development efficiency.
AnythingMCP empowers you to quickly and securely integrate your enterprise systems with the latest AI agents, enhancing automation and intelligence across your operations without extensive coding.
Links
Explore AnythingMCP further using these official resources:
- GitHub Repository: https://github.com/HelpCode-ai/anythingmcp
- Try on Cloud: https://cloud.anythingmcp.com
- Watch 90-sec demo: https://anythingmcp.com/en/video-promo
- Setup Guides: https://anythingmcp.com/guides
- Docker Hub: https://hub.docker.com/r/helpcodeai/anythingmcp
Related repositories
Similar repositories that may be relevant next.

ctx-gate: LLM Context Gateway for Efficient Token Usage
September 16, 2026
ctx-gate is an LLM-agnostic context optimization proxy that reduces token consumption in AI interactions. It intelligently prunes conversation history and tool outputs, ensuring critical facts are retained without altering your workflow. Compatible with Anthropic and OpenAI APIs, ctx-gate helps developers manage LLM costs and maintain prompt fidelity.

ADL CLI: Scaffold Enterprise-Ready AI Agents with A2A Protocol
September 15, 2026
The ADL CLI is a powerful command-line tool designed to rapidly scaffold and manage enterprise-ready AI Agents. It leverages the YAML-based Agent Definition Language (ADL) to generate complete project structures, eliminating boilerplate and ensuring consistent patterns. This tool significantly accelerates the development of AI agents powered by the A2A (Agent-to-Agent) protocol.
Local LLM Linux Troubleshoot: An AI Agent for Linux Diagnostics
September 14, 2026
Local LLM Linux Troubleshoot is an AI-powered agent designed to diagnose and resolve issues on Linux systems. It leverages llama.cpp for local AI processing, offering system diagnostics, safe command execution, and support for Docker, CLI, and a web GUI. This tool provides a privacy-first approach to managing and troubleshooting your Linux environment.

OpenWorkProof: Verifiable Work Contracts for AI Agent Systems
September 13, 2026
OpenWorkProof is an open protocol designed to bring transparency and accountability to AI agent work. It establishes verifiable contracts for multi-agent systems, ensuring that tasks are authorized, executed within agreed scopes, and independently verifiable. This protocol addresses critical questions about authorization, execution evidence, and human acceptance in AI-driven workflows.
Source repository
Open the original repository on GitHub.
16 counted GitHub visits