Jira MCP Server
Connect Jira to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Jira MCP Server. The jira mcp server is what makes that connection.
A collection of tools designed for interacting with Jira via the Model Context Protocol (MCP), providing core Jira functionalities and a unified, guided Issue Creation and Update Wizard.
@modelcontextprotocol/inspector on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
getJiraIssue — Fetches a Jira issue by its keyanalyzeJiraIssue — Performs comprehensive analysis of a Jira issuejiraGet — Fetches data from any Jira API GET endpointgetIssuesByJql — Searches for Jira issues using a JQL queryissueCreation_getState — Gets the current internal state of the wizardissueCreation_getStatus — Gets the high-level status of the wizardissueCreation_initiateState — Initializes a new wizard stateissueCreation_resetState — Resets the wizard stateissueCreation_updateState — Updates the wizard state (project, issue type, fields, step)issueCreation_createIssue — Creates a Jira issue using the wizard's stateissueCreation_getProjects — Retrieves available Jira projectsissueCreation_getIssueTypes — Gets available issue types for the selected projectConfiguration is passed through the environment: DEBUG, LOG_FILE_PATH, JIRA_BASE_URL, JIRA_API_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Among the planning and project tracking options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Jira's toolset — getJiraIssue, analyzeJiraIssue, jiraGet and 11 more — is a fair guide to whether it matches your workflow. It is maintained by timbreeding; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| getJiraIssue | Fetches a Jira issue by its key. |
| analyzeJiraIssue | Performs comprehensive analysis of a Jira issue. |
| jiraGet | Fetches data from any Jira API GET endpoint. |
| getIssuesByJql | Searches for Jira issues using a JQL query. |
| issueCreation_getState | Gets the current internal state of the wizard. |
| issueCreation_getStatus | Gets the high-level status of the wizard. |
| issueCreation_initiateState | Initializes a new wizard state. |
| issueCreation_resetState | Resets the wizard state. |
| issueCreation_updateState | Updates the wizard state (project, issue type, fields, step). |
| issueCreation_createIssue | Creates a Jira issue using the wizard's state. |
| issueCreation_getProjects | Retrieves available Jira projects. |
| issueCreation_getIssueTypes | Gets available issue types for the selected project. |
| issueCreation_getFields | Retrieves fields required for the selected project/issue type. |
| issueCreation_updateFields | Updates specific field values in the wizard state. |
{
"mcpServers": {
"jira-1": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/inspector"],
"env": {
"DEBUG": "your-value",
"LOG_FILE_PATH": "your-value",
"JIRA_BASE_URL": "your-value",
"JIRA_API_TOKEN": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| DEBUG | Configuration value read at startup. | Optional |
| LOG_FILE_PATH | Filesystem location the server is allowed to use. | Optional |
| JIRA_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| JIRA_API_TOKEN | Credential the server authenticates with. | Yes |
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.