MCP Connector

Route and Manage AI Agent Resources

Wanaku is an MCP router that centralizes access to tools and resources, bridging to other MCP servers and 400+ Camel integrations.

Works with keycloakapache camelkubernetesopenshift

91
Spark score
out of 100
Updated 11 days ago
Version 0.2.0
Models
universal

Add to Favorites

Why it matters

Centralize routing and resource management for AI agents, acting as a gateway between multiple MCP servers with extensive integration capabilities.

Outcomes

What it gets done

01

Provide unified access to AI agents and resources.

02

Bridge MCP servers for seamless inter-server communication.

03

Leverage 300+ Apache Camel components for broad integration.

04

Secure access with built-in authentication and authorization.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-wanaku-mcp-router | bash

Overview

Wanaku MCP Router MCP Server

Wanaku MCP Router centralizes access to MCP tools and resources for AI agents, bridging to other MCP servers and integrating external systems through 400+ Apache Camel components, with Kubernetes-native deployment and optional Keycloak authentication. Use it when managing multiple MCP tools, resource providers, or downstream MCP servers that need central routing, namespace isolation, or broad system integration; skip it for a single simple MCP server with no routing needs.

What it does

Wanaku MCP Router is a router for AI-enabled applications built on the Model Context Protocol, acting as a central point that connects AI agents to tools, resources, and other MCP servers. Rather than an agent connecting to each tool or MCP server individually, Wanaku provides unified, centralized routing, can act as an MCP-to-MCP bridge or gateway to other MCP servers, and taps into 400+ Apache Camel components for broad integration with external systems.

When to use - and when NOT to

Use this when you're managing multiple MCP tools, resource providers, or downstream MCP servers and want a single routing layer in front of them - especially useful for organizing tools and resources across isolated namespaces, or when deploying on Kubernetes/OpenShift with first-class native support. It suits teams building or operating AI agent infrastructure at some scale. It is not needed for a single, simple MCP server with no routing or bridging requirements - in that case connecting directly is simpler. Authentication via Keycloak is optional and can be run without auth, though that trades off the built-in security.

Capabilities

  • Unified access: centralized routing and resource management for AI agents across multiple backends.
  • MCP-to-MCP bridge: acts as a gateway or proxy in front of other MCP servers.
  • Extensive connectivity: leverages 400+ Apache Camel components to integrate with external systems.
  • Secure by default: built-in authentication and authorization via Keycloak, optional and can be disabled.
  • Kubernetes-native: first-class support for deployment on Kubernetes and OpenShift.
  • Extensible architecture: supports adding custom tools and resource providers.
  • Multi-namespace support: organizes tools and resources across isolated namespaces.

How to install

Download the CLI from the releases page, unpack it, and start a local instance:

wanaku start local

Then access the dashboard at http://localhost:8080. For guided learning, follow the tutorial at wanaku.ai/docs/demos/; full installation and configuration instructions are in the usage guide at wanaku.ai/docs/version/.

Who it's for

Teams operating multiple MCP tools, resource providers, or MCP servers who want a single, centrally managed routing layer - particularly those deploying on Kubernetes/OpenShift or needing broad system integration through Apache Camel.

Source README

Wanaku - A MCP Router that connects everything

License
Build
Release

The Wanaku MCP Router is a router for AI-enabled applications powered by the Model Context Protocol (MCP).

This protocol is an open protocol that standardizes how applications provide context to LLMs.

The project name comes from the origins of the word Guanaco, a camelid native to
South America.

Key Features

  • Unified Access - Centralized routing and resource management for AI agents
  • MCP-to-MCP Bridge - Act as a gateway or proxy for other MCP servers
  • Extensive Connectivity - Leverage 400+ Apache Camel components for integration
  • Secure by Default - Built-in authentication and authorization via Keycloak (optional - can run without auth)
  • Kubernetes-Native - First-class support for OpenShift and Kubernetes deployments
  • Extensible Architecture - Easy to add custom tools and resource providers
  • Multi-Namespace Support - Organize tools and resources across isolated namespaces

Quick Start

Getting started is a single command. Download the CLI from releases page, unpack,
and then just run:

wanaku start local

Access http://localhost:8080 to enter the dashboard:

Learn Wanaku

The easiest way to learn Wanaku is by following the guided tutorial.

Basic Usage

The reference documentation, including the complete installation and configuration instructions, is available on the usage guide.

Documentation

The Wanaku Documentation website contains additional documentation, covering several of
components that are part of the project - some of which are hosted in different repositories (i.e.: such as the
Camel Integration Capability,
the Java SDK, etc.).

Community

Contributors working on the project may want to refer to the development version of the documentation including

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.