mcp-conf-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CONFLUENCE_PAT | No | Your Confluence personal access token used for authentication. | |
| CONFLUENCE_COOKIE | No | Confluence authentication cookie, used as an alternative to a personal access token. | |
| CONFLUENCE_BASE_URL | Yes | Base URL of your Confluence Server / Data Center instance, including any context path if needed, e.g. https://example.com/confluence. | |
| CONFLUENCE_AUTH_MODE | No | Set to browser to use SSO through installed Chrome. Call conf_browser_login, complete sign-in, then retry. | |
| CONFLUENCE_BROWSER_CHANNEL | No | Optional browser channel for browser-based SSO authentication. | |
| CONFLUENCE_BROWSER_PROFILE | No | Optional Chrome profile path for browser-based SSO authentication. Defaults to ~/.mcp-conf-server/chrome-profile; protect it as a credential. | |
| CONFLUENCE_BROWSER_LOGIN_URL | No | Optional browser login URL for browser-based SSO authentication. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| conf_browser_loginB | Open browser for Confluence SSO sign-in |
| conf_browser_auth_statusC | Check browser authentication |
| conf_get_current_userB | Get authenticated user |
| conf_searchC | Search content using CQL; returns one page with pagination metadata |
| conf_get_spacesC | List spaces (one page) |
| conf_get_spaceC | Get space details |
| conf_get_pageB | Read page with storage XHTML body, version and ancestors |
| conf_get_childrenC | List child pages (one page) |
| conf_create_pageC | Create page; body must be Confluence storage XHTML |
| conf_update_pageB | Update page using the current version returned by get_page. Conflicts are returned without retry. |
| conf_delete_pageC | Move a page to trash |
| conf_get_commentsC | List page comments (one page) |
| conf_add_commentC | Add comment using storage XHTML |
| conf_get_labelsC | List labels (one page) |
| conf_add_labelC | Add global label |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 15 tools
Each tool maps to a distinct resource+action pair: auth (login/auth_status/current_user), spaces, pages, children, comments, labels. The only near-overlap is conf_browser_auth_status vs. conf_get_current_user, but the descriptions make the split clear (browser session state vs. resolved identity).
Strong conf_ namespace with consistent verb_noun forms (get_page, create_page, update_page, delete_page, add_comment, get_labels). Minor deviations: conf_search lacks a noun, and the two browser auth tools use a noun_first pattern (browser_login, browser_auth_status).
15 tools sits in the sweet spot and each one earns its place across six coherent sub-areas (auth, search, spaces, pages, comments, labels). Nothing feels duplicated or padded.
Page lifecycle is fully covered (create/get/update/delete plus children), but comments and labels are add-only with no update/delete, spaces are read-only, and attachments/version history—core Confluence concepts—are entirely absent. Agents will hit dead ends for cleanup or binary content workflows.