Jira MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | Host to bind for HTTP transport, e.g. 127.0.0.1 | |
| MCP_PORT | No | Port to bind for HTTP transport, e.g. 8003 | |
| JIRA_EMAIL | Yes | Jira Cloud account email used for Basic auth | |
| MCP_JWKS_URI | No | JWKS URI for inbound JWT authentication (required for HTTP without MCP_JWT_SECRET) | |
| JIRA_API_PATH | No | Jira API path, defaults to /rest/api/3 | /rest/api/3 |
| JIRA_BASE_URL | Yes | Jira site origin, e.g. https://your-site.atlassian.net | |
| MCP_READ_ONLY | No | Set to 'true' to hide the create_issue tool | |
| MCP_TRANSPORT | No | Transport mode, e.g. 'http' for remote HTTP server (default is stdio) | |
| JIRA_API_TOKEN | Yes | Jira API token used for Basic auth | |
| MCP_JWT_ISSUER | No | Expected JWT issuer for inbound authentication | |
| MCP_JWT_SECRET | No | JWT secret for inbound authentication (alternative to MCP_JWKS_URI) | |
| JIRA_ISSUE_TYPE | No | Default issue type, defaults to 'Task' | Task |
| MCP_JWT_AUDIENCE | No | Expected JWT audience for inbound authentication | |
| JIRA_DESCRIPTION_FORMAT | No | Description format: 'adf' (Cloud v3) or 'plain' (Data Center v2) | |
| JIRA_SOURCE_TICKET_FIELD | No | Custom field id for Source Ticket #, e.g. customfield_10001 | |
| JIRA_CUSTOMER_ORDER_FIELD | No | Custom field id for Customer Order #, e.g. customfield_10002 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_issueA | Read a Jira issue key, status, summary, Source Ticket #, and Customer Order #. |
| create_issueB | Create a Jira work item. Cloud v3 descriptions are sent as Atlassian Document Format. Source Ticket # and Customer Order # are written when those customfield ids are configured. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| health_resource |
TDQS
Scored across 2 tools
get_issue and create_issue have unambiguous, non-overlapping purposes — one reads, one writes. An agent can select correctly without hesitation.
Both tools follow a clean, predictable verb_noun snake_case pattern (get_issue, create_issue), consistent with common MCP conventions.
Only 2 tools for a server branded as a general 'Jira MCP' is thin; it covers just a narrow read/create slice of the Jira domain and leaves the set feeling minimally scoped.
Create and get are present but there is no update, delete, search, transition, or comment operation, so agents hit dead ends for common Jira workflows. The narrow customfield focus partially excuses the gap but not fully.