RT (Request Tracker) MCP Server
for AI Agents
Connect your AI agent to StackOne's RT (Request Tracker) MCP server and give it 24 MCP tools out of the box. Auth, tool execution, and security all managed.
StackOne 
Coverage
24 Agent Actions
Create, read, update, and delete across RT (Request Tracker) — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your RT (Request Tracker) MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every RT (Request Tracker) tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every RT (Request Tracker) call.
Tools Discovery →What is the RT (Request Tracker) MCP Server?
A RT (Request Tracker) MCP server lets AI agents read and write RT (Request Tracker) data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's RT (Request Tracker) MCP server ships with 24 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All RT (Request Tracker) MCP Tools
Every action from RT (Request Tracker)'s API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Ticket Attachments
- Get Ticket Attachments
List the attachments on a ticket
Attachments
- Get Attachment
Retrieve a single attachment by its ID
Custom Fields
- Create Custom Field
Create a new custom field definition
- List Custom Fields
List the custom fields defined in RT
- Get Custom Field
Retrieve a single custom field by its ID
Queues
- Create Queue
Create a new queue
- List Queues
List the queues the authenticated user can see
- Get Queue
Retrieve a single queue by its ID or name
Queue Custom Fields
- Get Queue Custom Fields
List the ticket custom fields applied to a queue
Tickets
- Create Ticket
Create a new ticket in a queue
- Search Tickets
Search tickets using TicketSQL, simple search, or a saved search
- Get Ticket
Retrieve a single ticket by its ID
- Update Ticket
Update a ticket's metadata (subject, status, owner, priority, custom fields, links)
- Delete Ticket
Delete a ticket (sets its status to deleted)
Take Tickets
- Take Ticket
Take ownership of an unowned ticket
Untake Tickets
- Untake Ticket
Release ownership of a ticket you own
Steal Tickets
- Steal Ticket
Take ownership of a ticket currently owned by someone else
Reply To Tickets
- Reply To Ticket
Add a public reply (correspondence) to a ticket
Comment On Tickets
- Comment On Ticket
Add an internal comment to a ticket (not sent to requestors)
Ticket Historys
- Get Ticket History
Retrieve the list of transactions (history) for a ticket
Transactions
- Search Transactions
Search transactions using TransactionSQL
- Get Transaction
Retrieve a single transaction by its ID
Users
- List Users
List users, optionally filtered by a JSON search query
- Get User
Retrieve a single user by ID or username
Set Up Your RT (Request Tracker) MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to RT (Request Tracker) in under 10 lines of code.
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Check More support-ticketing MCP Servers
105+ actions
42+ actions
37+ actions
34+ actions
11+ actions
Platform Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
MCP vs A2A: Architecture, Security, and When to Use Each
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP vs API: What 200+ Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
RT (Request Tracker) MCP Server FAQ
Does StackOne have a RT (Request Tracker) MCP server?
RT (Request Tracker) MCP server vs direct API integration — what's the difference?
How does RT (Request Tracker) authentication work for AI agents?
origin_owner_id.Are RT (Request Tracker) MCP tools vulnerable to prompt injection?
What is the context bloat of a RT (Request Tracker) agent and how do I avoid it?
Can I limit which actions my RT (Request Tracker) agent can access?
Can I create custom agent actions for my RT (Request Tracker) MCP server?
When should I NOT use a RT (Request Tracker) MCP server?
What AI frameworks and AI clients does the StackOne RT (Request Tracker) MCP server support?
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.