Edge

io.github.getedgehqv0.6.20Updated Oct 8, 2026

Gives your agent the right public skill for each task and loads it on demand.

VerifiedStreamable HTTPWeb executableAI & ML

Overview

AI-generated overview

Edge gives an AI assistant the right public skill for each task and loads it on demand.

What it does
Edge is a remote MCP server that supplies an assistant with public skills matched to the task at hand and loads them on demand. The registry description states it gives your agent the right public skill for each task and loads it on demand. No individual tools are listed in the manifest, so the exact operations are not documented here.
When to use it
Consider it when you want an assistant to pull in task-specific public skills dynamically rather than having them bundled in advance. It may suit general-purpose agents that need to adapt to varied tasks.
Requirements
It runs as a remote streamable HTTP endpoint at getedge.cc; no local package, environment variables, or headers are declared. The manifest declares no authentication, so no credentials are documented.
Before you install
The manifest declares no authentication and no credentials, and no tools are listed, so what data the server receives or changes cannot be verified from this input. Review the provider's own documentation before connecting an assistant.

Installation

In SourceWeft

  1. Open Edge in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "edge": {
      "type": "http",
      "url": "https://getedge.cc/mcp"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.6.20LatestOct 8, 2026