@cardor/agent-harness-kit

data-ai MCP Server

A provider-agnostic scaffolding kit for running structured multi-agent workflows in your codebase.

VerifiedInstall Ready
data-aidata-ai
4 views170 stars8 forksv1.7.5NOASSERTION

Why This Matters

Discovered via github-topic:mcp and last synced 3mo ago.

VerifiedInstall Ready
Source
github-topic:mcp
Stars
170
Last synced
3mo ago
Install
Instructions detected

Install

1. Install the package

npx @cardor/agent-harness-kit

2. Add to claude_desktop_config.json

{
  "mcpServers": {
    "-cardor-agent-harness-kit": {
      "command": "npx",
      "args": [
        "@cardor/agent-harness-kit"
      ]
    }
  }
}

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)

11
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (11)

Tool

lead

criterionId

Mark an acceptance criterion as met. Criterion IDs come from `tasks.acceptance_get`

query

Search the `docsPath` folder for content matching the query

View

What it shows

Runtime

SQLite

Purpose

Edit it?

File

Commit?

mjs

cjs} ├── AGENTS.md ├── health.sh ├── .harness/ └── .codex/ ├── config.toml ← MCP server registration └── agents/ ├── lead.toml ├── explorer.toml ├── builder.toml ├── reviewer.toml └── default.toml ← overrides Codex's built-in default agent → routes to lead ``` ### What each file does

taskId

Returns all acceptance criteria for a task with their `id`, `task_id`, `criterion` text, and `met` status. Use the returned `id` values with `tasks.acceptance.update`

consultant

builder

Role

Responsibility