confluence-adf-mcp
# confluence-adf-mcp
[](LICENSE)
MCP server for reading and writing Confluence pages in native ADF (Atlassian Document Format).
## Why this exists
Confluence stores pages in [ADF (Atlassian Document Format)](https://developer.atlassian.com/cloud/jira/platform/apis/document/structure/), a structured JSON format. Most tools convert to/from HTML or plain text, losing structure, formatting, and metadata in the process. This MCP server works with ADF directly, so edits are precise — find/replace, table updates, and mention swaps happen at the document node level without corrupting the surrounding content.
## Setup
### Requirements
- Python 3.12+
- A Confluence Cloud instance with API access
### Environment variables
```bash
export CONFLUENCE_URL="https://your-domain.atlassian.net/wiki"
export CONFLUENCE_USERNAME="you@example.com"
export CONFLUENCE_API_TOKEN="your-api-token"
```
Generate an API token at https://id.atlassian.com/manage-profile/security/api-tokens.
### OAuth 2.0 (optional)
Instead of basic auth, you can use OAuth 2.0 (3LO). Set these three environment variables:
```bash
export CONFLUENCE_OAUTH_CLIENT_ID="your-oauth-client-id"
export CONFLUENCE_OAUTH_CLIENT_SECRET="your-oauth-client-secret"
export CONFLUENCE_OAUTH_REFRESH_TOKEN="your-initial-refresh-token"
```
If all three are set, the server uses OAuth automatically; otherwise it falls back to basic auth (`CONFLUENCE_USERNAME` / `CONFLUENCE_API_TOKEN`).
Rotating refresh tokens are persisted to `.oauth_tokens.json` in the cache directory so the server can restart without re-authorizing. The cache directory defaults to `$XDG_CACHE_HOME/confluence-adf-mcp` (or `~/.cache/confluence-adf-mcp`); set `CACHE_DIR` to override it.
See [Atlassian OAuth 2.0 (3LO) documentation](https://developer.atlassian.com/cloud/confluence/oauth-2-3lo-apps/) for how to create an OAuth app and obtain the initial refresh token.
### Claude Code configuration
Copy `.env.example` to `.env` and fill in your credentials. The server loads `.env` automatically.
Add to `.claude/settings.json`:
```json
{
"mcpServers": {
"confluence-adf": {
"command": "uvx",
"args": ["--from", "git+https://github.com/karbassi/confluence-adf-mcp", "confluence-adf-mcp"]
}
}
}
```
## Shared HTTP server
By default every client starts its own stdio process. To run one long-lived server that many clients share:
```bash
CONFLUENCE_ADF_MCP_TRANSPORT=http CONFLUENCE_ADF_MCP_PORT=8506 confluence-adf-mcp
```
```json
{
"mcpServers": {
"confluence-adf": { "type": "http", "url": "http://127.0.0.1:8506/mcp" }
}
}
```
| Variable | Default | Description |
|---|---|---|
| `CONFLUENCE_ADF_MCP_TRANSPORT` | `stdio` | `stdio` or `http` (streamable HTTP at `/mcp`) |
| `CONFLUENCE_ADF_MCP_HOST` | `127.0.0.1` | Bind address. Only `127.0.0.1`, `localhost`, or `::1`; anything else exits |
| `CONFLUENCE_ADF_MCP_PORT` | `8506` | TCP port |
| `CONFLUENCE_ADF_MCP_ALLOWED_HOSTS` | | Extra comma-separated `Host` header values to accept, e.g. a reverse proxy's `mcp.example.com` |
| `CONFLUENCE_ADF_MCP_ALLOWED_ORIGINS` | | Extra comma-separated `Origin` values to accept, e.g. `https://mcp.example.com` |
`FASTMCP_HOST` / `FASTMCP_PORT` have no effect; use the variables above.
The endpoint has **no authentication**. It holds your Atlassian credentials, and its tools can edit, move, archive, and restrict pages and delete attachments. Anything that can connect to it acts as you. So:
- The server only binds to loopback. Any local process can still connect, so only use HTTP mode on a machine where every local user and process is trusted with your Atlassian account.
- DNS-rebinding protection is always on: requests whose `Host` is not `127.0.0.1:<port>`, `localhost:<port>` (or an entry in `CONFLUENCE_ADF_MCP_ALLOWED_HOSTS`) are rejected with `421`, and cross-site `Origin`s with `403`. That check **only** stops web pages from reaching the server through a rebound DNS name. It does not authenticate anyone.
- To reach it from another machine, put it behind a reverse proxy that **controls who can connect** (bearer token, mTLS, an IP allowlist on a private network, or similar) and add the proxy's hostname to `CONFLUENCE_ADF_MCP_ALLOWED_HOSTS`. Never expose the port or the proxy publicly without access control.
File paths always refer to the filesystem of the machine **running the server**, not the client's:
- `confluence_get_page` returns the absolute path of the cached copy to edit. A remote client can't open it, so use the edit tools (`confluence_edit_page`, `confluence_find_replace`, ...) instead of editing the file directly.
- `confluence_upload_attachment` reads, and `confluence_download_attachment` writes, paths on the server machine.
Each MCP session gets its own page cache under `<cache dir>/sessions/<session>/`, so clients sharing one server can't see, overwrite, or clear each other's cached pages. If a client reconnects it gets a new session, so call `confluence_get_page` again before editing. Session directories untouched for `CONFLUENCE_ADF_MCP_CACHE_TTL_HOURS` (default `168`, i.e. 7 days; `0` disables) are deleted at startup and at most hourly while the server runs.
## Tools
### Pages
| Tool | Description |
|------|-------------|
| `confluence_get_page` | Fetch a page and cache it locally |
| `confluence_create_page` | Create a new page with ADF content |
| `confluence_push_page` | Push cached page edits to Confluence |
| `confluence_extract_text` | Extract plain text from a page |
| `confluence_copy_page` | Duplicate a page |
| `confluence_archive_page` | Archive a page (with confirmation) |
| `confluence_move_page` | Move a page to a new parent (with confirmation) |
| `confluence_revert_page` | Revert a page to a previous version |
### Editing
| Tool | Description |
|------|-------------|
| `confluence_edit_page` | Find/replace text in cached page |
| `confluence_find_replace` | Fetch, find/replace, and push in one step |
| `confluence_regex_replace` | Regex find/replace on a page |
| `confluence_replace_mention` | Swap @mentions between users |
| `confluence_add_link` | Add a hyperlink to a page |
### Tables
| Tool | Description |
|------|-------------|
| `confluence_update_table_cell` | Update a single table cell |
| `confluence_insert_table_row` | Insert a row into a table |
| `confluence_delete_table_row` | Delete a row from a table |
### Tasks
| Tool | Description |
|------|-------------|
| `confluence_update_task` | Toggle task checkbox state (DONE/TODO) |
### Discovery
| Tool | Description |
|------|-------------|
| `confluence_search_pages` | Search pages with CQL |
| `confluence_list_pages` | List pages in a space |
| `confluence_get_child_pages` | Get child pages |
| `confluence_get_ancestors` | Get parent chain |
| `confluence_list_spaces` | List spaces |
| `confluence_get_contributors` | Get unique page contributors |
| `confluence_get_user` | Resolve account ID to display name |
### Labels
| Tool | Description |
|------|-------------|
| `confluence_get_labels` | Get labels on a page |
| `confluence_add_labels` | Add labels to a page |
| `confluence_remove_label` | Remove a label from a page |
### Versions
| Tool | Description |
|------|-------------|
| `confluence_list_versions` | List version history |
| `confluence_compare_versions` | Diff two versions as text |
### Comments
| Tool | Description |
|------|-------------|
| `confluence_add_comment` | Add a footer comment |
| `confluence_list_comments` | List footer comments |
| `confluence_add_inline_comment` | Add an inline annotation comment |
| `confluence_list_inline_comments` | List inline comments |
### Attachments
| Tool | Description |
|------|-------------|
| `confluence_list_attachments` | List attachments on a page |
| `confluence_upload_attachment` | Upload a file as an attachment |
| `confluence_download_attachment` | Download an attachment to a local file |
| `confluence_delete_attachment` | Delete an attachment (with confirmation) |
### Properties
| Tool | Description |
|------|-------------|
| `confluence_get_page_properties` | Get content properties |
| `confluence_set_page_property` | Set a content property |
### Access Control
| Tool | Description |
|------|-------------|
| `confluence_set_restrictions` | Set read/update restrictions |
| `confluence_watch_page` | Watch or unwatch a page |
### Cache
| Tool | Description |
|------|-------------|
| `confluence_list_cache` | List locally cached pages |
| `confluence_clear_cache` | Clear page cache |
## Contributing
See [CONTRIBUTING.md](CONTRIBUTING.md).
TDQS
Scored across 43 tools
Each tool has a clearly distinct purpose, covering different Confluence operations like page CRUD, content editing, comments, labels, attachments, etc. No two tools perform the same action; even similar tools like 'edit_page' and 'find_replace' differ in their workflow (multi-step vs. single-step).
All tool names follow a consistent 'confluence_verb_noun' pattern using snake_case (e.g., confluence_get_page, confluence_add_labels, confluence_delete_attachment). Compound operations combine verbs (confluence_find_replace) but remain predictable. No mixing of conventions.
43 tools is on the high side but appropriate for a comprehensive Confluence integration covering pages, spaces, comments, labels, attachments, versions, caching, etc. Some tools (like cache management) could be considered auxiliary, but overall scope justifies the count.
Major operations are covered but notable gaps exist: no permanent page deletion (only archive), no direct ADF body retrieval, no comment editing or deletion, and no separate tool to update page title. The find/replace and cache-based editing approach may hinder programmatic workflows.