What is confluence-mcp-server CLAUDE.md?

A project guide for an MCP server that connects AI agents with Confluence, a tool for managing team documentation. It sets rules for exploring spaces, finding existing pages, and creating or editing documents.

Use it before creating or editing Confluence pages, especially when you need to inspect spaces, folders, child pages, and related existing content.

It prevents agents from guessing where content belongs or creating duplicate pages. It also keeps new documentation consistent with the existing Confluence structure.

How Hamza-XP/confluence-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Hamza-XP/confluence-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Hamza-XP/confluence-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Hamza-XP/confluence-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hamza-xp/confluence-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/hamza-xp/confluence-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/hamza-xp/confluence-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/hamza-xp/confluence-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hamza-xp/confluence-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/hamza-xp/confluence-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,214 This file is loaded in full into every session.

When invoked 1,214 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01214	$0.01214
Opus 5.5	$0.00486	$0.00486
Sonnet 5.5	$0.00243	$0.00243
Haiku 4.5	$0.00121	$0.00121

Measured 22d ago against content hash 8a977489ff34, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

confluence-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude (or any agent) using this MCP server's tools to work with Confluence. Read this before creating or editing any page — it defines the house style so that content from different people and different sessions stays consistent.

Before creating anything: explore first, never guess

Call list_spaces to get real space keys. Display names in the UI often differ from the key (e.g. a space titled "Portali" may have key Portali1).
Call list_children on the space's home page, then recurse into any folders it returns, to build the actual structure before deciding where new content goes. Confluence Cloud has a native "Folder" content type distinct from pages — always let list_children show you both (this server's implementation already queries /child/page and /child/folder and merges them; if you're extending this server, preserve that).
Call search_pages for the topic you're about to document. If a page already covers it, update it or skip it — do not create a duplicate. Only write new pages for material that genuinely isn't there yet.
Match the existing convention in that space/folder (flat numbered pages vs. nested folders, emoji-prefixed titles vs. plain, etc.) rather than imposing your own structure.

Standard document structure

When compiling infrastructure or task documentation (as opposed to editing something freeform), use this section order. Omit a section entirely if you have no real source material for it — never fabricate content to fill a template:

Overview — one paragraph: what this system/project is
Repositories — links and relevant branches, if applicable
AWS Account & Region (or equivalent cloud provider info) — a table: component, region, notes
Architecture — key components and how they connect
Environment Variables / Configuration — what's documented; see the credentials note below before including actual values
Deployment Runbook — concrete, step-by-step, copy-pasteable commands
CI/CD Pipeline — if documented
Supporting Infrastructure — anything that doesn't fit above (CDN, WAF, monitoring, etc.)
Known Issues / Troubleshooting
Open Questions / Gaps — things referenced but unexplained, or where sources conflict

Read the full file on GitHub · 96 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

22d ago Changed · +5 lines · +59 tokens per session 8a977489ff34
2mo ago First seen · 91 lines · 1,155 tokens per session scan A 4278f11c3018

Subscribe to this mod's changes

confluence-mcp-server CLAUDE.md is an instructions file published in the GitHub repository Hamza-XP/confluence-mcp-server (3 stars, last pushed 23d ago), licensed MIT. It adds 1,214 tokens to every session, about $0.0049 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

confluence-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
confluence-mcp-server CLAUDE.mdHamza-XP/confluence-mcp-server	Instructions file	3	23d ago	MIT	A	1,214	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

confluence-mcp-server: Instructions file for Claude Code