Hamilton Harness MCP Server

by sharathkum05 Your server? Claim it

local only

Hamilton Harness runs on your own machine — the client starts it, so there is no endpoint to ping. 26 installs a week from npm.

Manage your Hamilton Harness AI rep: knowledge, rules, orders, tests and conversations.

Installs per day peak 309 · avg 11

a month agotoday

Installs / week

npm · hamilton-harness

—

Stars

on GitHub

—

Last commit

2 releases in 90 days

—

License

language unknown

Nothing serious here today

Today is the operative word: we check Hamilton Harness every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add hamilton-harness -- npx -y hamilton-harness

~/Library/Application Support/Claude/claude_desktop_config.json

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

~/.codex/config.toml

[mcp_servers.hamilton-harness]
command = "npx"
args = ["-y", "hamilton-harness"]

.cursor/mcp.json

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

.vscode/mcp.json

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

This one needs environment variables set before it will start: HAMILTON_URL (Address of your Hamilton Harness server, such as https://chat.example.com), HAMILTON_ADMIN_TOKEN (The admin token the server prints when started with --admin). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Hamilton Harness

same job, measured the same way

Darwin

by meetdarwin

Read and manage your Darwin website AI agent: conversations, leads, meetings, knowledge and tests.

answering

ONES

by ones

Manage ONES projects, issues, tests, work hours, and Wiki knowledge.

answering

Decisionrules

by decisionrules

Create, manage, and test business rules directly from your AI agent via the DecisionRules platform.

answering

Testiny Test Management

by testiny

Create and manage test cases, test runs and results in Testiny from your AI assistant.

answering

Mida

by mida

Create, run and analyze A/B tests and personalizations on your site with Mida.

answering

ThunderPhone

by thunderphone

Build, test, deploy and run AI phone agents: agents, numbers, calls, tests, knowledge, campaigns.

24 installs/wk answering

RuleDrift

by ri7in

Test whether AI agents retain critical instructions as conversations grow.

61 installs/wk local only

Tesults MCP

by tesults

Ask your AI agent why your tests are failing. Instant analysis on failures and regressions.

20 installs/wk local only

Hamilton Harness — questions

Answers built from our own checks of this server.

Why is there no uptime for Hamilton Harness?

Hamilton Harness runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package hamilton-harness was installed 26 times last week.

How do I connect Hamilton Harness?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls hamilton-harness straight from npm; nothing to host, nothing to sign up for.

How many people use Hamilton Harness?

The npm package hamilton-harness was installed 26 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.