Skip to main content
Glama
Sign In
confluence-mcp

confluence-mcp

by lucaszzz1202
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Confluence MCP Server

MCP server for Confluence integration — read, write, search, and manage attachments via the Confluence REST API.

Installation

npm install -g @mcd/confluence-mcp-server

Or use with npx:

npx @mcd/confluence-mcp-server

Related MCP server: confluence-mcp

Configuration

Add to your MCP settings (e.g. ~/.kiro/settings/mcp.json):

{
  "mcpServers": {
    "confluence-mcp": {
      "command": "npx",
      "args": ["@mcd/confluence-mcp-server@latest"],
      "env": {
        "CONFLUENCE_URL": "https://your-confluence.atlassian.net",
        "CONFLUENCE_USERNAME": "your-email@example.com",
        "CONFLUENCE_TOKEN": "your-api-token",
        "CONFLUENCE_CLOUD": "true"
      }
    }
  }
}

For local development, point directly to the compiled output:

{
  "mcpServers": {
    "confluence-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/dist/index.js"],
      "env": {
        "CONFLUENCE_URL": "...",
        "CONFLUENCE_USERNAME": "...",
        "CONFLUENCE_TOKEN": "...",
        "CONFLUENCE_CLOUD": "false"
      }
    }
  }
}

Environment Variables

Variable

Description

CONFLUENCE_URL

Your Confluence instance URL

CONFLUENCE_USERNAME

Your username or email

CONFLUENCE_TOKEN

Your API token or password

CONFLUENCE_CLOUD

"true" for Cloud, "false" for Server

Available Tools

Pages

  • search — Search Confluence content (CQL)

  • get_page — Get page content by ID

  • get_page_children — Get child pages of a parent page

  • create_page — Create a new page

  • update_page — Update page content (inline HTML or file path)

Attachments

  • get_attachments — List attachments on a page

  • download_attachment — Download an attachment to local disk

  • upload_attachment — Upload a local file as a page attachment, with optional embedding in page body

Comments

  • get_comments — Get page comments

  • add_comment — Add a comment to a page

Tool Examples

Search:

{ "query": "space = DEV AND title ~ \"API\"", "limit": 10 }

Update page with inline content:

{ "page_id": "123456", "content": "<h1>Title</h1><p>Updated content</p>" }

Update page from file (recommended for large content):

{ "page_id": "123456", "content_file": "/absolute/path/to/content.html" }

Upload attachment:

{ "page_id": "123456", "file_path": "/absolute/path/to/file.png" }

Upload and embed in page body:

{
  "page_id": "123456",
  "file_path": "/absolute/path/to/image.png",
  "embed_in_body": true,
  "comment": "Optional comment"
}

Images are embedded as <ac:image>, other files as a view-file macro link.

Development

npm install
npm run build

Available Tools

10 tools
add_commentB

Add a comment to a Confluence page

Inputs: content (required), page_id (required).

create_pageC

Create a new Confluence page

Inputs: title (required), content (required), space_key (required), parent_id.

download_attachmentB

Download a Confluence attachment

Inputs: page_id (required), output_path (required), attachment_id (required).

get_attachmentsB

Get attachments from a Confluence page

Inputs: page_id (required).

get_commentsB

Get comments from a Confluence page

Inputs: page_id (required), limit, start.

get_pageC

Get Confluence page content

Inputs: page_id (required), include_body.

get_page_childrenB

Get child pages of a Confluence page

Inputs: parent_id (required), limit, start.

searchB

Search Confluence content

Inputs: query (required), limit.

update_pageA

Update a Confluence page with new content.

IMPORTANT: For large HTML files, use 'content_file' parameter to provide the file path. The tool automatically handles:

  • Escaping unescaped & characters to &amp;

  • Cleaning HTML structure (removes DOCTYPE, html, head, body tags)

Inputs: page_id (required), title, content, minor_edit, +1 more.

upload_attachmentA

Upload a file as an attachment to a Confluence page. The file must be specified by its absolute path on the local filesystem. Optionally embed the attachment in the page body.

Inputs: page_id (required), file_path (required), comment, embed_in_body.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.5/5.0

    Scored across 10 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action: search, page retrieval, children, attachments (list vs download), comments (list vs add), page create/update, and attachment upload. No two tools appear to do the same thing.

    Naming Consistency4/5

    Most names follow a clear verb_noun pattern (get_page, create_page, update_page, upload_attachment). The mix of verbs like search, get, download, add, create, update, upload is reasonable and readable, though not perfectly uniform.

    Tool Count5/5

    With 10 tools, the set is well-scoped for a Confluence MCP server covering search, page content, comments, and attachments. Each tool has a clear role without feeling excessive.

    Completeness3/5

    Core content operations are covered (search, read, create, update, comment, attachments), but there are no delete operations for pages, comments, or attachments. This is a notable gap for full lifecycle management, though typical workflows are still possible.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers