wanaku
Wanaku MCP Router
claude mcp add --transport stdio wanaku-ai-wanaku docker run -i wanaku/wanaku:latest \ --env WANAKU_BASE_URL="URL of Wanaku router (e.g., http://localhost:8080)" \ --env WANAKU_ADMIN_USER="admin username (placeholder)" \ --env WANAKU_ADMIN_PASSWORD="admin password (placeholder)"
How to use
Wanaku is an MCP Router that acts as a central hub for MCP-enabled tools and resources. It provides unified access, MCP-to-MCP bridging, and secure routing with built-in authentication. Once running, you can authenticate against the Wanaku router, list available tools and resources, and add new tools to the router to extend its capabilities. The included CLI commands demonstrated in the project README show how administrators interact with Wanaku to manage authentication, tool registration, and resource discovery, enabling seamless context provisioning for connected LLMs and agents.
How to install
Prerequisites:
- Java 21 or later (required for Wanaku CLI as described in the repository).
- Docker (if you choose to run Wanaku via Docker).
- Optional: JBang installed for Java-based installation.
Installation options:
-
Java/JBang installation (recommended for developers):
- Ensure Java 21+ is installed.
- Install Wanaku via JBang: jbang app install wanaku@wanaku-ai/wanaku
- Follow the usage guide in the repository for starting and configuring Wanaku.
-
Docker-based installation:
- Ensure Docker is running.
- Start Wanaku from the Docker image: docker run -i wanaku/wanaku:latest
-
Download binaries (if available):
- Download the latest Wanaku binary from the releases page and run according to the provided instructions in the release notes.
Configuration:
- After starting Wanaku, configure authentication (e.g., Keycloak), tools, and resources through the Wanaku UI or CLI as described in the documentation.
- Refer to docs/usage.md and docs/configurations.md for detailed configuration options and examples.
Additional notes
Tips and considerations:
- Java 21+ is required to run Wanaku via the provided CLI installation method.
- If using Docker, ensure proper network access and environment variable configuration for authentication and base URL.
- Wanaku supports MCP-based tooling; you can register tools via the CLI or UI to expose their MCP capabilities to LLMs and other agents.
- When troubleshooting, check Wanaku logs for authentication failures, tool registration errors, and MCP bridge activity.
- Review the Security documentation to configure and enforce access control and keys properly.
- If you plan to deploy on Kubernetes/OpenShift, follow the Kubernetes-Native deployment guidance in the Architecture/Configuration docs.
Related MCP Servers
volcano-agent-sdk
🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few lines of TypeScript.
cursor10x
The Cursor10x MCP is a persistent multi-dimensional memory system for Cursor that enhances AI assistants with conversation context, project history, and code relationships across sessions.
okta
The Okta MCP Server is a groundbreaking tool built by the team at Fctr that enables AI models to interact directly with your Okta environment using the Model Context Protocol (MCP). Built specifically for IAM engineers, security teams, and Okta administrators, it implements the MCP specification to help work with Okta enitities
zerodha
Zerodha MCP Server & Client - AI Agent (w/Agno & w/Google ADK)
symfony
A Symfony package designed for building secure servers based on the Model Context Protocol, utilizing Server-Sent Events (SSE) and/or StreamableHTTP for real-time communication. It offers a scalable tool system tailored for enterprise-grade applications.
branch-thinking
Branch-Thinking MCP Tool A TypeScript-powered MCP server for managing parallel branches of thought, semantic cross-references, and persistent tasks. Features dynamic scoring, AI-generated insights, batch operations, and visual graph navigation for advanced agentic workflows.
