mcpField
H
Harness

Harness

Local
github.com/asklokeshCloud & Infra0Updated 43w ago
Repository

About Harness

Harness is an MCP server that connects GenAI applications to Harness for continuous delivery and cloud cost management through its API. It includes multiple authentication methods, rate limiting, error handling with retries, and asynchronous support.

Key features

  1. 01Broad Harness API coverage
  2. 02Multiple authentication methods
  3. 03Rate limiting
  4. 04Error handling and retries
  5. 05Asynchronous support

Use cases

  1. 01Connecting GenAI applications to Harness
  2. 02Handling API requests with retries
  3. 03Using Harness with different authentication methods

MCP support

Exposes Harness API capabilities to MCP clients, enabling GenAI applications to integrate with Harness.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "asklokesh-harness": {
      "command": "uvx",
      "args": [
        "harness-mcp-server"
      ],
      "env": {
        "HARNESS_API_KEY": "<HARNESS_API_KEY>",
        "HARNESS_API_URL": "<HARNESS_API_URL>"
      }
    }
  }
}
Run commanduvx harness-mcp-server
Environment variables to set
HARNESS_API_KEYSecretAPI Key for HARNESS
HARNESS_API_URLAPI URL for HARNESS

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiharness-mcp-server0.1.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Harness MCP Server

Harness Mcp Server

GitHub stars GitHub forks GitHub watchers

License Issues Pull Requests Last Commit

Python MCP

Commit Activity Code Size Contributors

A Model Context Protocol (MCP) server for integrating Harness with GenAI applications.

Overview

Continuous delivery and cloud cost management

Features

  • Comprehensive Harness API coverage
  • Multiple authentication methods
  • Enterprise-ready with rate limiting
  • Full error handling and retry logic
  • Async support for better performance

Installation

pip install harness-mcp-server

Or install from source:

git clone https://github.com/asklokesh/harness-mcp-server.git
cd harness-mcp-server
pip install -e .

Configuration

Create a .env file or set environment variables according to Harness API requirements.

Quick Start

from harness_mcp import HarnessMCPServer

# Initialize the server
server = HarnessMCPServer()

# Start the server
server.start()

License

MIT License - see LICENSE file for details

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.