jira_search_issuesLABSCO SUMMARY
Query languages exposed properly — JQL and CQL, not just keyword search.
Both servers hand the real query language through, which is what makes them useful for anything beyond looking up one ticket: the assistant can express the filter precisely rather than guessing at a search box. They are two processes with two credential sets, so register both if you want work to move between a ticket and the page that documents it.
What it is
A Python project holding two separate MCP servers, one for Jira and one for Confluence, each launched independently and registered separately in your client.
What you get
- Jira:
jira_search_issuesby JQL,jira_get_issue,jira_create_issue,jira_update_issue,jira_add_comment,jira_transition_issueandjira_get_projects - Confluence:
confluence_search_contentby CQL,confluence_get_page,confluence_create_page,confluence_update_page,confluence_delete_page - Confluence structure tools too:
confluence_get_spaces,confluence_get_page_childrenandconfluence_add_attachment - Worked call examples for search, creation, transition and page update
Requirements
uv sync, then credentials per product: JIRA_URL, JIRA_USERNAME, JIRA_API_TOKEN and JIRA_CLOUD, and the matching CONFLUENCE_ set. Set the cloud flag to true for Atlassian Cloud, false for Server. Register both servers in the client, each pointing at its own shell script in the project root.
Setup effort
One command plus a key — uvx jira-mcp, then supply credentials
USE CASES
01
Reviewing what is in flight
Search issues with a JQL filter for the project and status you care about, and summarise them.
02
Writing up what shipped
Find the issues, then create the Confluence page in the right space with the summary.
03
Keeping documentation current
Search pages by CQL, read the one that is stale, and update it with a version comment.
15 tools
Listed in project docs. Your client may show a different list.
jira_get_issuejira_create_issuejira_update_issuejira_add_commentjira_transition_issuejira_get_projectsconfluence_search_contentconfluence_get_pageconfluence_create_pageconfluence_update_pageconfluence_delete_pageconfluence_get_spacesconfluence_get_page_childrenconfluence_add_attachmentBEFORE YOU INSTALL
What to know first
Tools you get
15 tools named in the project's documentation.
Requires
- uvx on PATH
- JIRA_API_TOKEN in your environment
- CONFLUENCE_API_TOKEN in your environment
- JIRA_USERNAME in your environment
- CONFLUENCE_USERNAME in your environment
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx jira-mcpMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"jira": {
"command": "<YOUR_PATH_TO_JIRA_CONFLUENCE_MCP>/run_jira.sh",
"args": [],
"env": {
"JIRA_URL": "https://<YOUR_DOMAIN>.atlassian.net",
"JIRA_USERNAME": "<YOUR_JIRA_USERNAME>",
"JIRA_API_TOKEN": "<YOUR_JIRA_API_TOKEN>",
"JIRA_CLOUD": "true"
}
},
"confluence": {
"command": "<YOUR_PATH_TO_JIRA_CONFLUENCE_MCP>/run_confluence.sh",
"args": [],
"env": {
"CONFLUENCE_URL": "https://<YOUR_DOMAIN>.atlassian.net",
"CONFLUENCE_USERNAME": "<YOUR_CONFLUENCE_USERNAME>",
"CONFLUENCE_API_TOKEN": "<YOUR_CONFLUENCE_API_TOKEN>",
"CONFLUENCE_CLOUD": "true"
}
}
}
}
