Skip to main content
Glama

Tests Release


CAI MCP Toolkit extends AI assistants with specialized tools for Cox Automotive workflows. Connect your IDE to Rally, GitHub Enterprise, New Relic, Salesforce, and more through the Model Context Protocol.

Choose Your Setup Guide

Experience Level

Guide

Description

Comfortable with the command line

Windows Setup / macOS Setup

Jump straight into installation, configuration, and IDE setup.

Prefer a guided, step-by-step setup

Getting Started Guide

Everything explained from scratch -- no technical experience needed.

Not sure where to start

Slack: #ai-mcp

Your team lead or manager can help determine the right path, or ask us on Slack.

Related MCP server: AegisX MCP

Features

  • Extensive Tool Library for Rally, GitHub, Salesforce, and more — plus 30+ hosted remote MCP servers (New Relic, Datadog, Splunk, PagerDuty, and more) and bundled MCPs for Jira, Figma, and Confluence

  • Multiple IDE Support for VS Code, JetBrains IDEs, and Claude Code

  • Configurable - enable only the tools you need via YAML configuration

  • Extensible - add bundled, local, or remote MCP servers

  • Web UI - browser-based interface for configuration and tool exploration

  • Self-Diagnosing - built-in doctor command and rescue mode for troubleshooting

Quick Install

Download and run the installer for your platform:

Platform

Download

VS Code

VS Code Insiders

Windows x64

Download

Configure

Configure

macOS Intel

Download

Configure

Configure

macOS Apple Silicon

Download

Configure

Configure

macOS Users: The installer is not yet notarized. See macOS Security Warnings for workarounds.

Command Line

For step-by-step installation instructions, see macOS Setup or Windows Setup.

# Verify installation
cai-mcp --version

# Generate configuration
cai-mcp generate-config

# Launch web UI for configuration
cai-mcp web

Claude Desktop

Claude Desktop uses .mcpb manifest bundle files. Download the bundle for your platform and follow the Claude Desktop setup guide.

Platform

Architecture

Download

Windows

x64

cai-mcp-windows-x64.mcpb

macOS

Intel (x64)

cai-mcp-macos-x64.mcpb

macOS

Apple Silicon (arm64)

cai-mcp-macos-arm64.mcpb

Note: All releases including pre-release betas are available on the Releases page.

Binary Downloads

For manual installation or headless/Linux systems, download the binary directly.

All releases: Browse all versions including pre-release betas on the Releases page.

Platform

Architecture

Download

Linux

x64

cai-mcp-linux-x64

Linux

arm64

cai-mcp-linux-arm64

macOS

x64

cai-mcp-macos-x64

macOS

arm64

cai-mcp-macos-arm64

Windows

x64

cai-mcp-win-x64.exe

Quick Start

  1. Install using the GUI installer above

  2. Configure your IDE by clicking the "VS Code Configure" button, or see setup guides for:

  3. Enable tools by editing your config file (~/.caimcp/config.yaml on macOS/Linux, %USERPROFILE%\.caimcp\config.yaml on Windows):

    tools:
      includeCategories:
        - 'Rally'
        - 'Github: Issues'
        - 'Github: Pulls'
        - 'Github: Repos'
        - 'Github: Search'
        - 'Web'
        - 'Utility'
      # Hosted remote MCP servers are opt-in and authenticate through a browser
      # sign-in on first use (not via local API keys):
      includeRemoteMCPs:
        - newrelic
        - splunk
  4. Restart your IDE to load the MCP server

That's it! Ask your AI assistant to use Rally or GitHub tools. The first time you use a remote MCP (New Relic, Splunk, …) a browser window opens to sign you in through the gateway.

What's Included

Component

Description

Details

Tools

Rally, GitHub, Salesforce, and more local tools

Tool Reference

Prompts

Reusable prompt templates

Prompt Reference

Resources

MCP resources for logs and references

Resource Reference

Bundled MCPs

Third-party MCP servers (Figma, Confluence, etc.)

Bundled MCPs

Remote MCPs

Hosted MCP servers (New Relic, Datadog, Splunk, GitHub, Atlassian, Postman, and 25+ more)

Remote MCPs

Note: Most tools are disabled by default. Edit your configuration to enable the categories you need.

Documentation

Topic

Description

Getting Started

Getting Started Guide

Guided setup -- no technical experience needed

macOS Setup

Full installation and IDE setup for macOS

Windows Setup

Full installation and IDE setup for Windows

Configuration

Configuration Guide

YAML config, tool filtering, MCP servers

API Key Setup

Rally and local-tool tokens (remote-MCP credentials are entered at the gateway, not here)

Reference

CLI Commands

All available commands

Troubleshooting

Doctor command, rescue mode, common issues

CLI Quick Reference

cai-mcp                     # Start MCP server (default)
cai-mcp web                 # Launch web configuration UI
cai-mcp list-tools          # List all available tools
cai-mcp list-tools --filtered  # List only enabled tools
cai-mcp doctor              # Diagnose configuration issues
cai-mcp update              # Check for and install updates
cai-mcp --help              # Show all commands

Contributing

We welcome contributions! See the Contributing Guide for:

  • Development setup

  • Creating new tools

  • Testing guidelines

  • Git workflow and conventional commits

Support


Contributors

F
license - not found
Not graded
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    A
    quality
    D
    maintenance
    A personal AI coding assistant that connects to various development environments and helps automate tasks, provide codebase insights, and improve coding decisions by leveraging the Model Context Protocol.
    10
  • A
    license
    Not graded
    quality
    C
    maintenance
    Provides AI assistants with access to AegisX UI components, CRUD generator commands, development patterns, and API contract discovery tools. It enables developers to browse component documentation, build generation commands, and test authenticated API endpoints through the Model Context Protocol.
    20
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Enables AI assistants to interact with Azure DevOps, providing tools for managing work items, repositories, pipelines, and more through the Model Context Protocol.
    100
    11
    MIT

View all related MCP servers

Related MCP Connectors

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/QNSC-VN/mcp-tools'

If you have feedback or need assistance with the MCP directory API, please join our Discord server