Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CONFLUENCE_URLYesThe URL of your Confluence instance, e.g., https://your-domain.atlassian.net/wiki
CONFLUENCE_EMAILYesYour Atlassian account email address
CONFLUENCE_TOKENYesYour Atlassian API token

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

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
upload_pageA

Upload Markdown to Confluence at SPACE ROOT level or UPDATE existing page.

⚠️ ROUTING RULES:

  • Page URL provided → UPDATES that existing page (ignores parentId)

  • Space key/URL only → Creates NEW page at space root level

❌ DO NOT use this tool to create child/sub-pages. ✅ Use 'create_child_page' tool instead for hierarchical pages.

Mermaid diagrams are auto-converted to images.

update_pageC

Update an existing Confluence page with Markdown content

list_spacesA

List available Confluence spaces. NOTE: Do NOT use this before upload_page. Only use when user explicitly asks to browse/list spaces. For uploads, ask user directly for space key or URL.

search_pagesC

Search for Confluence pages

sync_fileA

Sync a LOCAL file to a Confluence page. This tool reads the file directly from the filesystem.

⚠️ CRITICAL INSTRUCTIONS FOR AI:

  • file_path MUST be the EXACT path specified by the user

  • Do NOT infer or guess file path based on Confluence page title or URL content

  • If user says "sync readme.md to URL", find "readme.md" file, NOT files matching page title

  • If multiple files match, ask user to specify the exact path

  • This tool handles file reading internally - just pass the path

Examples:

  • User: "sync readme.md to https://..." → file_path: "/path/to/readme.md" (find readme.md)

  • User: "sync /docs/guide.md to https://..." → file_path: "/docs/guide.md" (exact path)

create_child_pageA

Create a NEW page as a child (sub-page) of an existing page.

⚠️ MUST USE THIS TOOL WHEN:

  • User wants to create a page "under", "below", "하위에", or "beneath" another page

  • User provides a parent page URL and wants NEW content added as a sub-page

  • User says "put this under [page]", "[page] 하위에 넣어줘", "add as child of [page]"

❌ WARNING: upload_page with a page URL will UPDATE that page, NOT create a child. ✅ ALWAYS use create_child_page for hierarchical page creation.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.7/5.0

Scored across 6 tools

Disambiguation4/5

The tools are mostly distinct with clear purposes, but there is some potential confusion between 'upload_page' and 'create_child_page' for page creation scenarios, as both involve creating pages but under different conditions. The descriptions provide explicit routing rules to mitigate this, but an agent might still need to carefully parse user intent to choose correctly.

Naming Consistency5/5

All tool names follow a consistent snake_case pattern with clear verb_noun structures (e.g., create_child_page, list_spaces, search_pages, sync_file, update_page, upload_page). This consistency makes the tool set predictable and easy to understand at a glance.

Tool Count5/5

With 6 tools, the server is well-scoped for its purpose of managing Confluence pages from Markdown files. The count is appropriate, covering key operations like listing, searching, creating, updating, and syncing without being overwhelming or too sparse.

Completeness4/5

The tool set covers essential CRUD-like operations for Confluence pages (create, update, sync, list, search), but there are minor gaps such as the lack of a delete_page tool for full lifecycle management. However, agents can likely work around this by using other methods or the existing tools for most workflows.

Maintenance

ActivityNo data
ResponsivenessNo issues