Agent Academy

Agent Academy is a free, source-linked library of skills, prompts, MCP servers and bot templates, organised into courses by profession, for people who hand real work to AI agents: 1,467 live resources, each with its original link, license and safety tags.

MCP server

Jitbit Helpdesk

MCP server for Jitbit Helpdesk: search, list, read, and reply to support tickets from AI assistants.

Needs credentialsCan send externally

https://github.com/jitbit/jitbit-helpdesk-mcp

Needs credentials

JITBIT_URL, JITBIT_TOKEN, Authorization

Install
npx -y jitbit-helpdesk-mcp

Original content

Full originalMITSource

Republished in full under its license, with attribution. The source is authoritative.

Jitbit Helpdesk MCP Server

An MCP (Model Context Protocol) server that lets AI assistants search and read support tickets from Jitbit Helpdesk. Works with both SaaS and on-premise installations.

> ⚠️ Use the hosted HTTP endpoint when possible. Jitbit ships a built-in HTTP MCP endpoint at /api/mcp on all SaaS and on-premise installs running version 11.21 or later. That is the preferred way to connect AI assistants to Jitbit — no local install, always in sync with Jitbit releases. See the Jitbit MCP docs. Starting with 2.x, this npm package is a thin stdio proxy to that same endpoint, for clients that don't yet support remote HTTP MCP servers. Jitbit 11.21 or later is required. If you're on an older on-premise version, stay on jitbit-helpdesk-mcp@1.x.

Setup

Two options:

  1. Hosted HTTP endpoint (recommended) — connect your MCP client directly to Jitbit's /api/mcp. Use this whenever your client supports HTTP MCP transport.
  2. Local npm package (stdio proxy) — this repo. Use it when your MCP client only supports stdio transport. It forwards every request to {JITBIT_URL}/api/mcp and adds nothing of its own.

Option 1: Hosted HTTP endpoint

Claude Code

claude mcp add --transport http jitbit-helpdesk https://yourcompany.jitbit.com/api/mcp \
  --header "Authorization: Bearer your-api-token"

Claude Desktop, Cursor, Windsurf

{
  "mcpServers": {
    "jitbit-helpdesk": {
      "type": "http",
      "url": "https://yourcompany.jitbit.com/api/mcp",
      "headers": {
        "Authorization": "Bearer your-api-token"
      }
    }
  }
}

Option 2: Local npm package (stdio proxy)

Claude Code

claude mcp add jitbit-helpdesk \
  -e JITBIT_URL=https://yourcompany.jitbit.com \
  -e JITBIT_TOKEN=your-api-token \
  -- npx -y jitbit-helpdesk-mcp

Claude Desktop, Cursor, Windsurf

Add to your config file:

  • Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
  • Cursor: Settings > MCP Servers
  • Windsurf: Settings > MCP Servers
{
  "mcpServers": {
    "jitbit-helpdesk": {
      "command": "npx",
      "args": ["-y", "jitbit-helpdesk-mcp"],
      "env": {
        "JITBIT_URL": "https://yourcompany.jitbit.com",
        "JITBIT_TOKEN": "your-api-token"
      }
    }
  }
}

Environment Variables

VariableRequiredDescription
JITBIT_URLYesBase URL of your Jitbit instance (SaaS: https://yourcompany.jitbit.com, on-prem: your server URL)
JITBIT_TOKENYesAPI token — see below

Getting your API token

  1. Log in to your Jitbit Helpdesk
  2. Go to your User Profile (click your avatar in the top right)
  3. Click the "API Token" button
  4. Copy the token and use it as the JITBIT_TOKEN value

Tools

The proxy exposes whatever tools the connected Jitbit instance advertises at /api/mcp — typically ticket search, list, and read, plus anything Jitbit adds in later releases. Use your MCP client's tool listing (or the Jitbit MCP docs) for the up-to-date catalog.

Development

npm install
npm run build

License

MIT

DescriptionMCP server for Jitbit Helpdesk: search, list, read, and reply to support tickets from AI assistants.
Version2.0.0
Packagesnpm · jitbit-helpdesk-mcp@2.0.0 · stdio
Environment variablesJITBIT_URL required
Base URL of your Jitbit Helpdesk instance
JITBIT_TOKEN required secret
API token from your Jitbit user profile
Remote endpointsstreamable-http https://{helpdesk_host}/api/mcp

Related

TutorialCustomer service

2_1_support_ticket_agent

A structured output agent demonstrating Pydantic schema-based responses for customer support ticket creation.

Sourcegithub.com/Shubhamsaboo/awesome-llm-apps/tree/main/ai_agent_framework_crash_course/openai_sdk_crash_course/2_structured_output_agent/2_1_support_ticket_agent

No credentialsDoes not sendApache-2.0
TutorialCustomer service

3_1_customer_support_ticket_agent

A tutorial demonstrating how to implement a structured customer support ticketing system using Google's ADK (Agent Development Kit) framework. This example shows how to create type-safe, structured support tickets with priority levels, categories, and resolution estimates using Pydantic schemas and

Sourcegithub.com/Shubhamsaboo/awesome-llm-apps/tree/main/ai_agent_framework_crash_course/google_adk_crash_course/3_structured_output_agent/3_1_customer_support_ticket_agent

No credentialsDoes not sendApache-2.0
CaseCustomer service

ai_customer_support_agent

This Streamlit app implements an AI-powered customer support agent for synthetic data generated using GPT-4o. The agent uses OpenAI's GPT-4o model and maintains a memory of past interactions using the Mem0 library with Qdrant as the vector store.

Sourcegithub.com/Shubhamsaboo/awesome-llm-apps/tree/main/advanced_ai_agents/single_agent_apps/ai_customer_support_agent

No credentialsDoes not sendApache-2.0
TutorialCustomer service

Using tool_choice=required for customer service (OpenAI cookbook)

Using Tool Required for Customer Service The ChatCompletion endpoint now includes the ability to specify whether a tool must be called every time, by adding tool_choice='required' as a parameter. This adds an element of determinism to how you build your wrapping application, as you can count on a to

Sourcegithub.com/openai/openai-cookbook/blob/main/examples/Using_tool_required_for_customer_service.ipynb

No credentialsDoes not sendMIT
TutorialCustomer service

Customer service agent with tool use (Claude cookbook)

Creating a Customer Service Agent with Client-Side Tools In this recipe, we'll demonstrate how to create a customer service chatbot using Claude 3 plus client-side tools. The chatbot will be able to look up customer information, retrieve order details, and cancel orders on behalf of the customer. We

Sourcegithub.com/anthropics/claude-cookbooks/blob/main/tool_use/customer_service_agent.ipynb

No credentialsDoes not sendMIT
Awesome listCustomer service

500 AI Agents Projects (includes customer service use cases)

Curated collection of AI agent use cases across industries (incl. Customer Service, E-commerce) with links to open-source implementations, e.g. a LangGraph customer-support agent tutorial.

Sourcegithub.com/ashishpatel26/500-AI-Agents-Projects

No credentialsDoes not sendMIT