confluence-http-api-mcp
Allows AI agents to read project documentation from Confluence, including searching pages, fetching content by ID or title, listing spaces, and navigating page trees.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@confluence-http-api-mcp search for pages about API design in the DEV space"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
confluence-http-api-mcp
Read-only MCP server for self-hosted Confluence (Server / Data Center) over the REST API.
Primary use case: let an AI agent read project documentation — search pages, fetch content, navigate page trees.
Requirements
Node.js 18+
Confluence base URL and a Personal Access Token with read access to the relevant spaces
Related MCP server: finviet-confluence-mcp
Configuration
Variable | Required | Description |
| Yes | Base URL, e.g. |
| Yes | PAT sent as |
Alias: CONFLUENCE_PAT.
Tools (read-only)
Tool | Purpose |
| CQL search ( |
| Page by content id + plain-text body |
| Page by space key + exact title |
| Discover spaces |
| Child pages (doc tree / TOC) |
Page bodies are returned as plain text (HTML/storage markup stripped) for easier agent consumption.
Install
From source (GitLab / GitHub)
git clone git@gitlab.greenworm.ru:ai/confluence-http-api-mcp.git
cd confluence-http-api-mcp
npm installПубличное зеркало: https://github.com/rkorablin/confluence-http-api-mcp.
From npm
npm install confluence-http-api-mcpOr globally (for npx / CLI usage):
npm install -g confluence-http-api-mcpUsage
Standalone (stdio)
export CONFLUENCE_URL="https://wiki.it-aces.com"
export CONFLUENCE_TOKEN="..."
node server.mjsCursor / MCP host
Add the server to your MCP config (for example .cursor/mcp.json → mcpServers).
Option 1: Local clone
"confluence": {
"command": "node",
"args": ["/absolute/path/to/confluence-http-api-mcp/server.mjs"],
"env": {
"CONFLUENCE_URL": "https://wiki.it-aces.com",
"CONFLUENCE_TOKEN": "..."
}
}Option 2: npm / npx
If installed globally:
"confluence": {
"command": "confluence-http-api-mcp",
"env": {
"CONFLUENCE_URL": "https://wiki.it-aces.com",
"CONFLUENCE_TOKEN": "..."
}
}Or via npx (рекомендуется для автоподтягивания новых версий):
"confluence": {
"command": "npx",
"args": ["--yes", "--prefer-online", "confluence-http-api-mcp@latest"],
"env": {
"CONFLUENCE_URL": "https://wiki.it-aces.com",
"CONFLUENCE_TOKEN": "..."
}
}Or via wrapper + secrets file (see ~/.config/ai-mcp pattern used for GitLab/YouTrack).
Typical agent workflow
confluence_list_spaces— find space key (e.g.GAR)confluence_searchwithspace=GAR AND title ~ "Architecture"confluence_get_page— read full page textconfluence_get_page_children— walk documentation hierarchy
License
MIT
Available Tools
5 toolsconfluence_get_pageA
Get a Confluence page by numeric content id. Returns title, space, ancestors and plain-text body.
Inputs: pageId (required), maxBodyChars.
confluence_get_page_by_titleA
Get a page by space key and exact title (first match).
Inputs: title (required), spaceKey (required), maxBodyChars.
confluence_get_page_childrenA
List child pages under a parent page (table of contents / doc tree).
Inputs: pageId (required), limit.
confluence_list_spacesA
List Confluence spaces accessible with the token.
Inputs: limit, start.
confluence_searchA
Search Confluence pages with CQL. Examples: space=GAR AND type=page, space=GAR AND title ~ "API", text ~ "address search" AND space=GAR. Returns titles, ids, excerpts.
Inputs: cql (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct resource or access pattern: search uses CQL, get_page uses numeric ID, get_page_by_title uses space+title, list_spaces enumerates spaces, and get_page_children navigates hierarchy. No two tools overlap in purpose.
All tools use a consistent 'confluence_' prefix followed by a verb_noun pattern. The two get_page variants are differentiated by suffix 'by_title', maintaining clarity.
Five tools is well-scoped for a read-only Confluence integration; each tool serves a distinct function without redundancy or excessive minimalism.
The core read operations are present: search, get by ID, get by title, list spaces, and list children. However, there are no mutation endpoints and no space-level detail tool, leaving minor gaps for a full API surface.
Maintenance
Related MCP Connectors
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
Read-only MCP server exposing a user ORANO library to their own AI agent.
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
Unofficial Confluence MCP — wraps the Confluence Cloud REST API v2 (OAuth)
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA read-only MCP server that enables querying and searching Atlassian Confluence pages and Jira issues through their REST APIs. Supports retrieving content by ID or URL, searching using CQL/JQL, and listing spaces and projects.1MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI agents to read Confluence page content by URL, supporting self-hosted Confluence with basic auth.-
- AlicenseNot gradedqualityDmaintenanceMCP server for reading Confluence Server/DC documents with search, page content, metadata, spaces, page tree, and attachment/image support.11 npmMIT
- AlicenseAqualityDmaintenanceMCP server for Confluence Server/Data Center (self-hosted) that gives LLM agents access to search, read, create/edit pages, comments, labels, and attachments via the Confluence REST API.15MIT