Connect
Optimize
Secure
Live 42 Actions
Jira Service Management MCP Server
for AI Agents
Connect your AI agent to StackOne's Jira Service Management MCP server and give it 42 MCP tools out of the box. Auth, tool execution, and security all managed.
Jira Service Management MCP Server
Built by 
StackOne
StackOne 
Coverage
42 Agent Actions
Create, read, update, and delete across Jira Service Management — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Jira Service Management MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Jira Service Management 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 Jira Service Management call.
Tools Discovery →What is the Jira Service Management MCP Server?
A Jira Service Management MCP server lets AI agents read and write Jira Service Management data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Jira Service Management MCP server ships with 42 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 Jira Service Management MCP Tools
Every action from Jira Service Management's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Request Comments
- Create Request Comment
Create a public or internal comment on a request
- List Request Comments
Get all comments on a customer request
- Get Request Comment
Get a specific comment on a customer request
Request Feedbacks
- Get Request Feedback
Get customer satisfaction feedback for a request
- Delete Request Feedback
Delete customer satisfaction feedback from a request
Organizations
- Create Organization
Create a new organization
- Get Organization
Get a specific organization by ID
- Delete Organization
Delete an organization
Request Participants
- Add Request Participants
Add participants to a customer request
- List Request Participants
Get all participants on a customer request
- Remove Request Participants
Remove participants from a customer request
Queues
- List Queues
Get all queues for a service desk
- Get Queue
Get a specific queue by ID
Requests
- Create Request
Create a new customer request in a service desk. Use list_service_desks to get serviceDeskId, list_service_desk_request_types to get requestTypeId, and pass requestFieldValues as an object with "summary" and optionally "description" fields
- Get Request
Get a specific customer request by issue ID or key
Service Desks
- List Service Desks
Get all service desks accessible to the user
- Get Service Desk
Get a specific service desk by ID
Other (25)
- Add Customers To Service Desk
Add customers to a service desk
- Create Customer
Create a new customer account
- Add Users To Organization
Add users to an organization. Pass accountIds as an array of Atlassian account ID strings. Use list_organization_users to see current members
- Add Organization To Service Desk
Add an organization to a service desk
- List Request Approvals
Get all approvals on a customer request
- List Service Desk Customers
Get customers associated with a service desk
- Get Info
Get runtime information about the JSM instance
- List All Organizations (Global)
Get all organizations across the entire Jira instance. For organizations linked to a specific service desk, use list_service_desk_organizations instead
- List Organization Users
Get all users in an organization
- List Organizations For Service Desk
Get organizations linked to a specific service desk. Requires a serviceDeskId. Use list_service_desks to find the service desk ID first. For all organizations globally, use list_organizations instead
- List Queue Issues
Get issues in a specific queue
- List Customer Requests
Get all customer requests accessible to the user
- List All Request Types (Global)
Get all request types across all service desks globally. Use this when you need request types from every service desk at once. For request types on a specific service desk, use list_service_desk_request_types instead
- List Request Types For Service Desk
Get all request types available on a specific service desk. Requires a serviceDeskId. Use list_service_desks to find the service desk ID first
- Get Request Type
Get a specific request type by ID on a service desk. Requires both serviceDeskId and requestTypeId. Use list_service_desk_request_types to find valid request type IDs
- Get Request Type Fields
Get the fields for a specific request type
- List Request Type Groups
Get request type groups for a service desk
- List All SLA Metrics
Get all SLA metric records for a customer request. Returns each SLA metric ID, name, and cycle details. Use a returned slaMetricId with get_request_sla_metric for full details on a specific metric
- Get SLA Metric By ID
Get a specific SLA metric by its ID for a customer request. Use list_request_sla_information first to get the slaMetricId
- Get Request Status
Get the status history of a customer request
- List Request Transitions
Get available workflow transitions for a request
- Remove Users From Organization
Remove users from an organization. Pass accountIds as an array of Atlassian account ID strings. Use list_organization_users first to get current member account IDs
- Remove Organization From Service Desk
Remove an organization from a service desk
- Post Request Feedback
Submit customer satisfaction feedback for a resolved request. Requires rating (1-5), type must be set to "csat", and comment must be an object with a "body" field
- Perform Request Transition
Perform a workflow transition on a customer request
Set Up Your Jira Service Management MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Jira Service Management 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
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
Jira Service Management MCP Server FAQ
Does StackOne have a Jira Service Management MCP server?
Yes. StackOne offers a hosted Jira Service Management MCP server with 42 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Jira Service Management MCP server vs direct API integration — what's the difference?
A Jira Service Management MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Jira Service Management. A Jira Service Management MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Jira Service Management at runtime. StackOne provides both.
How does Jira Service Management authentication work for AI agents?
Jira Service Management authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Jira Service Management account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Jira Service Management MCP tools vulnerable to prompt injection?
Yes — Jira Service Management MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Jira Service Management agent and how do I avoid it?
Context bloat happens when Jira Service Management tool schemas and API responses eat your Jira Service Management agent's memory, preventing it from reasoning effectively. A single Jira Service Management query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Jira Service Management agent can access?
Yes — you can limit which actions your Jira Service Management agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Jira Service Management MCP server?
Yes — you can create custom agent actions for your Jira Service Management MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Jira Service Management's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Jira Service Management MCP server?
Skip a Jira Service Management MCP server if your integration is purely software-to-software — direct Jira Service Management API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Jira Service Management actions at runtime.
What AI frameworks and AI clients does the StackOne Jira Service Management MCP server support?
The StackOne Jira Service Management MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
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.