Hyper
Hyper-MCP is an MCP server that leverages WebAssembly plugins to extend its capabilities.
It’s designed as a single, extensible MCP server that can be enhanced with plugins written in any WebAssembly-compatible programming language.
This approach allows you to add new functionality without the overhead of running multiple MCP servers.
Features
- 🌐 WebAssembly-first architecture
- 🔌 Easy plugin development with Extism PDKs
- 📦 OCI registry integration for plugin distribution
- 🔧 Simple configuration via JSON file
- 🚀 Compatible with various MCP applications (Claude Desktop, Cursor IDE, etc.)
Use Cases
- Developers can create custom tools and integrations for their MCP workflows without learning a specific plugin language
- Teams can distribute and update plugins easily using existing container infrastructure
- Enterprises can self-host plugins for enhanced security and compliance
- Researchers can quickly prototype and deploy new AI-assisted tools using familiar programming languages
How to Use It
1. Create a configuration file at $HOME/.config/mcp.json:
{
"plugins": [
{
"name": "time",
"path": "/path/to/time.wasm"
},
{
"name": "qr-code",
"path": "oci://ghcr.io/tuananh/qrcode-plugin:latest"
},
{
"name": "hash",
"path": "oci://ghcr.io/tuananh/hash-plugin:latest"
}
]
}2. Start the server:
$ hyper-mcp3. Integrate with your MCP-compatible application:
For Cursor IDE:
cursor mcp
cursor mcp chatClaude Desktop integration documentation is coming soon for Windows/macOS users.
4. Building plugins:
Hyper-MCP uses Extism for plugin development. Refer to example plugins like the QR Code Plugin and Hash Plugin for guidance.
5. Publishing plugins:
5.1 Build your WebAssembly plugin
5.2 Create a Dockerfile:
FROM scratch
WORKDIR /
COPY --from=builder /workspace/target/wasm32-wasip1/release/your-plugin.wasm /plugin.wasm5.3. Build and push:
docker build -t your-registry/plugin-name .
docker push your-registry/plugin-nameFAQs
Q: What programming languages can I use to create plugins for Hyper-MCP?
A: You can use any programming language that compiles to WebAssembly. This includes languages like Rust, C/C++, AssemblyScript, and many others.
Q: How does Hyper-MCP handle plugin updates?
A: Plugins distributed via OCI registries can be updated by pushing new versions to the registry. Users can then update their configuration file to point to the new version.
Q: Is it possible to use local plugins with Hyper-MCP?
A: Yes, you can use local plugins by specifying a file path in the configuration file instead of an OCI registry URL.
Q: How does Hyper-MCP ensure plugin security?
A: Hyper-MCP leverages WebAssembly’s sandboxed execution environment, which provides a level of isolation. However, users should still be cautious when using third-party plugins and review the plugin source code when possible.
Latest MCP Servers
CVE
WebMCP
webmcp is an MCP server that connects MCP clients to web search, page fetching, and local LLM-based extraction. It’s ideal…
Google Meta Ads GA4
Featured MCP Servers
Notion
Claude Peers
Excalidraw
FAQs
Q: What exactly is the Model Context Protocol (MCP)?
A: MCP is an open standard, like a common language, that lets AI applications (clients) and external data sources or tools (servers) talk to each other. It helps AI models get the context (data, instructions, tools) they need from outside systems to give more accurate and relevant responses. Think of it as a universal adapter for AI connections.
Q: How is MCP different from OpenAI's function calling or plugins?
A: While OpenAI's tools allow models to use specific external functions, MCP is a broader, open standard. It covers not just tool use, but also providing structured data (Resources) and instruction templates (Prompts) as context. Being an open standard means it's not tied to one company's models or platform. OpenAI has even started adopting MCP in its Agents SDK.
Q: Can I use MCP with frameworks like LangChain?
A: Yes, MCP is designed to complement frameworks like LangChain or LlamaIndex. Instead of relying solely on custom connectors within these frameworks, you can use MCP as a standardized bridge to connect to various tools and data sources. There's potential for interoperability, like converting MCP tools into LangChain tools.
Q: Why was MCP created? What problem does it solve?
A: It was created because large language models often lack real-time information and connecting them to external data/tools required custom, complex integrations for each pair. MCP solves this by providing a standard way to connect, reducing development time, complexity, and cost, and enabling better interoperability between different AI models and tools.
Q: Is MCP secure? What are the main risks?
A: Security is a major consideration. While MCP includes principles like user consent and control, risks exist. These include potential server compromises leading to token theft, indirect prompt injection attacks, excessive permissions, context data leakage, session hijacking, and vulnerabilities in server implementations. Implementing robust security measures like OAuth 2.1, TLS, strict permissions, and monitoring is crucial.
Q: Who is behind MCP?
A: MCP was initially developed and open-sourced by Anthropic. However, it's an open standard with active contributions from the community, including companies like Microsoft and VMware Tanzu who maintain official SDKs.
