Wassette

v1.0.0Securitystable

Wassette: A security-oriented runtime that runs WebAssembly Components via MCP

capabilitiesmcpmcp-serverocioci-artifacts
Share:
889
Stars
0
Downloads
0
Weekly
0/5

What is Wassette?

Wassette is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to wassette: a security-oriented runtime that runs webassembly components via mcp

Wassette: A security-oriented runtime that runs WebAssembly Components via MCP

This server falls under the Security and Developer Tools categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Wassette: A security-oriented runtime that runs WebAssembly

Use Cases

Wassette: A security-oriented runtime that runs WebAssembly Components via MCP
microsoft

Maintainer

LicenseMIT
Languagerust
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx wassette

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Wassette

Wassette is a security-oriented MCP runtime built by Microsoft that executes WebAssembly (Wasm) components in isolated sandboxes, exposing their capabilities as MCP tools to AI agents like Claude Code, GitHub Copilot, Cursor, and Gemini CLI. Components are distributed as OCI artifacts from registries like GitHub Container Registry, and each component runs in a Wasmtime sandbox with browser-grade isolation — preventing access to the host filesystem, network, or environment outside what the component explicitly declares. It is designed for scenarios where you want to extend AI agents with custom tools but cannot afford to run arbitrary native code with full host privileges.

Prerequisites

  • Linux or macOS (Windows support available via the installation guide)
  • curl available in your shell for the one-liner installer
  • An MCP-compatible AI client: Claude Code, GitHub Copilot (VS Code), Cursor, or Gemini CLI
  • Internet access to pull WebAssembly component artifacts from OCI registries (e.g., ghcr.io)
1

Install Wassette

Run the official install script to download the Wassette binary for your platform. The script installs to a standard location on your PATH.

curl -fsSL https://raw.githubusercontent.com/microsoft/wassette/main/install.sh | bash
2

Verify the installation

Confirm that wassette is installed and available by checking the version.

wassette --version
3

Configure your MCP client to use Wassette

Add Wassette as an MCP server in your AI client's configuration. Wassette acts as the runtime — you point your client at it and then load components on demand.

{
  "mcpServers": {
    "wassette": {
      "command": "wassette",
      "args": ["serve"]
    }
  }
}
4

Load a WebAssembly component via OCI URI

Ask your AI agent to load a component from an OCI registry. Wassette downloads, verifies, and runs it in an isolated Wasmtime sandbox, then exposes its tools to the agent.

5

Use the component's capabilities

Once loaded, the component's tools are available to the AI agent. In the time-server example, you can ask for the current time and Wassette relays the query to the sandboxed Wasm component.

Wassette Examples

Client configuration (Claude Code)

Configure Claude Code to use Wassette as the MCP runtime for WebAssembly components:

{
  "mcpServers": {
    "wassette": {
      "command": "wassette",
      "args": ["serve"]
    }
  }
}

Prompts to try

Interact with Wassette and WebAssembly components via natural language:

- "Please load the time component from oci://ghcr.io/microsoft/time-server-js:latest"
- "What is the current time?"
- "Load a calculator component and compute 2567 * 48"
- "What WebAssembly components are currently loaded?"
- "Unload the time component and confirm it is no longer available"

Troubleshooting Wassette

wassette command not found after running the install script

The install script places the binary in a directory that should be on your PATH, but you may need to restart your shell or run source ~/.zshrc (or ~/.bashrc). Check the script output for the install path and add it to your PATH manually if needed.

OCI component pull fails with 'manifest not found' or authentication error

Public components from ghcr.io should be accessible without authentication. For private registries, authenticate first using docker login or the relevant OCI tool, as Wassette respects the local credential store.

Component loads but its tools are not visible in the AI client

After loading a component, ask the AI client to refresh its tool list or restart the MCP connection. Some clients cache the tool manifest at connection time and need a reconnect to pick up newly loaded tools.

Frequently Asked Questions about Wassette

What is Wassette?

Wassette is a Model Context Protocol (MCP) server that wassette: a security-oriented runtime that runs webassembly components via mcp It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Wassette?

Follow the installation instructions on the Wassette GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Wassette?

Wassette works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Wassette free to use?

Yes, Wassette is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Wassette Alternatives — Similar Security Servers

Looking for alternatives to Wassette? Here are other popular security servers you can use with Claude, Cursor, and VS Code.

Casdoor

13.6k

An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD

ghidraMCP

9.0k

An Model Context Protocol server that enables LLMs to autonomously reverse engineer applications by exposing Ghidra's decompilation and analysis tools. It allows AI agents to list code structures, rename methods, and analyze binaries directly through

HexStrike AI

8.9k

HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly b

IDA Pro MCP

8.7k

Enables AI-assisted reverse engineering in IDA Pro by providing tools to analyze binaries, decompile functions, manage comments, search patterns, and interact with the IDA database through natural language.

Anthropic Cybersecurity Skills

6.6k

754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platform

Hooker

5.1k

🔥🔥 hooker is a Frida-based reverse engineering toolkit for Android. It offers a user-friendly CLI, universal scripts, auto hook generation, memory roaming to detect activities/services, one-click SOCKS5 proxy setup, Frida JustTrustMe, and BoringSSL u

Browse More Security MCP Servers

Explore all security servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "wassette": { "command": "npx", "args": ["-y", "wassette"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Wassette?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides