Confluence Communication MCP Server

Facilitates integration with Confluence and Jira by providing functionalities to execute queries and manage content.

Local serverstdio 28

What is the Confluence Communication MCP server?

Confluence Communication MCP server exists for a simple reason — assistants are far more useful when they can act on Confluence Communication directly instead of describing what you should do. Facilitates integration with Confluence and Jira by providing functionalities to execute queries and manage content.

What you get

This server implements the Model Context Protocol (MCP) for Confluence integration. This version addresses and fixes bugs found in the existing Confluence server, providing a more stable and reliable experience. It provides functionalities to execute CQL queries and retrieve page content from Confluence.

What the assistant can call

Once Confluence Communication is connected, these are the calls the assistant has available:

  • execute_cql_search — Executes a CQL query on Confluence to search pages
  • Description — Executes a CQL query on the Confluence instance to search for pages
  • get_page_content — Retrieves the content of a specific Confluence page
  • create_page — Creates a new Confluence page
  • update_page — Updates an existing Confluence page
  • execute_jql_search — Executes a JQL query on Jira to search issues
  • create_jira_issue — Creates a new Jira issue
  • update_jira_issue — Updates an existing Jira issue
  • transition_jira_issue — Changes the status of a Jira issue
  • get_board_sprints — Get all sprints from a Jira board
  • get_sprint_issues — Get all issues from a sprint
  • get_current_sprint — Get current active sprint from a board with its issues

Configuration and credentials

You will need 5 environment variables: CONFLUENCE_URL, JIRA_URL, CONFLUENCE_API_MAIL, CONFLUENCE_API_KEY, CONFLUENCE_IS_CLOUD. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

Installation goes through your MCP client rather than a global install: point it at @smithery/cli on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Choosing this one

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. Confluence Communication's toolset — execute_cql_search, Description, get_page_content and 11 more — is a fair guide to whether it matches your workflow. It is maintained by zereight; 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.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Confluence Communication.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the confluence communication mcp server does with a few real requests.

Available tools

ToolWhat it does
execute_cql_searchExecutes a CQL query on Confluence to search pages.
DescriptionExecutes a CQL query on the Confluence instance to search for pages.
get_page_contentRetrieves the content of a specific Confluence page.
create_pageCreates a new Confluence page.
update_pageUpdates an existing Confluence page.
execute_jql_searchExecutes a JQL query on Jira to search issues.
create_jira_issueCreates a new Jira issue.
update_jira_issueUpdates an existing Jira issue.
transition_jira_issueChanges the status of a Jira issue.
get_board_sprintsGet all sprints from a Jira board.
get_sprint_issuesGet all issues from a sprint.
get_current_sprintGet current active sprint from a board with its issues.
get_epic_issuesGet all issues belonging to an epic.
get_user_issuesGet all issues assigned to or reported by a specific user in a board.

How to install the Confluence Communication MCP server

{
  "mcpServers": {
    "Confluence communication server": {
      "command": "npx",
      "args": ["-y", "@zereight/mcp-confluence"],
      "env": {
        "CONFLUENCE_URL": "https://XXXXXXXX.atlassian.net",
        "JIRA_URL": "https://XXXXXXXX.atlassian.net",
        "CONFLUENCE_API_MAIL": "Your email",
        "CONFLUENCE_API_KEY": "KEY_FROM: https://id.atlassian.com/manage-profile/security/api-tokens",
        "CONFLUENCE_IS_CLOUD": "true" // Set to "false" for Server/Data Center
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
CONFLUENCE_URLEndpoint or connection string the server talks to.Yes
JIRA_URLEndpoint or connection string the server talks to.Yes
CONFLUENCE_API_MAILConfiguration value read at startup.Optional
CONFLUENCE_API_KEYCredential the server authenticates with.Yes
CONFLUENCE_IS_CLOUDConfiguration value read at startup.Optional

Example prompts to try

  • Use Confluence Communication to execute cql search.
  • Use Confluence Communication to Description.
  • Use Confluence Communication to get page content.

Frequently asked questions

The server is designed to work with applications supporting the Model Context Protocol (MCP) like Claude App, Cline, Roo Code, and Cursor. It can also be integrated into custom applications via API.