
Hamilton Harness
io.github.sharathkum05v0.1.1Updated Oct 4, 2026
Manage your Hamilton Harness AI rep: knowledge, rules, orders, tests and conversations.
Overview
AI-generated overview
Lets an assistant manage a Hamilton Harness AI rep, covering its knowledge, rules, orders, tests and conversations.
- What it does
- Hamilton Harness is a local MCP server that connects an assistant to your own Hamilton Harness deployment so it can administer an AI rep. According to its registry description, it covers knowledge, rules, orders, tests and conversations. The manifest does not list individual tools, so the exact operations are not documented here.
- When to use it
- Worth adding when you already run a Hamilton Harness server and want an assistant to help maintain the AI rep's knowledge, rules, orders, tests or conversations from your desktop.
- Requirements
- Runs as a local process over stdio, installed from the npm package hamilton-harness, so Node.js is needed. Requires the environment variables HAMILTON_URL (address of your Hamilton Harness server) and HAMILTON_ADMIN_TOKEN (admin token printed when the server is started with --admin). Desktop only; no web executable.
Before you install
The server requires HAMILTON_ADMIN_TOKEN, an administrative credential, so treat it as a secret and avoid exposing it. It can change the AI rep's knowledge, rules, orders, tests and conversations, so actions may write to or delete data in your Hamilton Harness deployment. No authentication method is declared in the manifest beyond that token.
Installation
In SourceWeft
- Open Hamilton Harness in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Tools
0Tool metadata has not been indexed yet.
Version history
1- v0.1.1LatestOct 4, 2026


