jira-readonly-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JIRA_TOKEN | Yes | Jira Cloud API token, or Jira Server/DC Personal Access Token. | |
| JIRA_BASE_URL | Yes | Base URL of your Jira instance (Cloud or Server/Data Center), no trailing slash. Example: https://your-company.atlassian.net | |
| JIRA_USERNAME | No | Required for Jira Cloud basic auth: your Atlassian account email. Leave unset for Server/DC bearer-token auth. | |
| JIRA_AUTH_TYPE | No | Optional: force the auth scheme instead of auto-detecting from JIRA_USERNAME. One of: basic | bearer | |
| JIRA_API_VERSION | No | Optional: Jira REST API version to call. Defaults to "2". | 2 |
| JIRA_MCP_LOG_LEVEL | No | Optional: diagnostic log verbosity. One of: debug | info | warn | error. Logs go to stderr. Defaults to "info". | info |
| JIRA_MAX_SEARCH_LIMIT | No | Optional: maximum number of results returned by search tools. | 50 |
| JIRA_REQUEST_TIMEOUT_MS | No | Optional: request timeout in milliseconds. | 15000 |
| JIRA_DEFAULT_SEARCH_LIMIT | No | Optional: default number of results returned by search tools. | 25 |
| JIRA_ACCEPTANCE_CRITERIA_FIELD | No | Optional: custom field ID that holds "Acceptance Criteria" in your Jira instance, e.g. customfield_10040. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_issueA | Fetch a single Jira issue by key (e.g. DEMO-123) as compact structured data: summary, description, status, type, priority, acceptance criteria (if configured), comments, and linked issues. Read-only. |
| search_issuesB | Search Jira issues using JQL (Jira Query Language) and return compact summaries. Read-only; results are capped by JIRA_MAX_SEARCH_LIMIT. |
| get_commentsB | Fetch comments for a Jira issue as compact structured data. Read-only. |
| get_related_issuesA | Fetch issues linked to a Jira issue: issue links, subtasks, and parent. Read-only. |
| get_my_open_issuesA | List unresolved Jira issues assigned to the authenticated user. Read-only. |
| get_project_metadataB | Fetch basic metadata for a Jira project (name, type, lead). Read-only. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Most tools have clearly distinct targets (single issue, JQL search, comments, links, my issues, project metadata). However, get_issue already returns comments and linked issues, so it partially overlaps with get_comments and get_related_issues, and get_my_open_issues is essentially a preset of search_issues. Descriptions do help clarify the intended use cases.
All names use snake_case with a verb_noun structure (get_issue, get_comments, get_related_issues, get_project_metadata, get_my_open_issues). The only deviation is search_issues, which is still readable and semantically appropriate for a query action rather than a fetch.
Six tools is well-scoped for a focused read-only Jira integration. Each tool maps to a distinct read operation with no filler or redundancy beyond the mild overlap noted.
The read-only surface covers the core read paths: fetch, search, comments, links/subtasks, assigned work, and project metadata. Minor gaps exist for read-only needs like attachments, worklogs, or listing all accessible projects, but these are workable omissions.