Atlassian ConfluenceSAFE
Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Transform how you access and interact with your team's knowledge by connecting Claude, Cursor AI, and other AI assistants directly to your Confluence spaces, pages, and documentation. Get instant answers from your knowledge base, search across all your spaces, and streamline your documentation workflow.
[](https://www.npmjs.com/package/@aashari/mcp-server-atlassian-confluence)
What You Can Do
- Ask AI about your documentation: "What's our API authentication process?"
- Search across all spaces: "Find all pages about security best practices"
- Get instant answers: "Show me the latest release notes from the Product space"
- Access team knowledge: "What are our HR policies for remote work?"
- Review page comments: "Show me the discussion on the architecture document"
- Create and update content: "Create a new page in the DEV space"
Perfect For
- Developers who need quick access to technical documentation and API guides
- Product Managers searching for requirements, specs, and project updates
- HR Teams accessing policy documents and employee resources quickly
- Support Teams finding troubleshooting guides and knowledge base articles
- Anyone who wants to interact with Confluence using natural language
Quick Start
Get up and running in 2 minutes:
1. Get Your Confluence Credentials
Generate a Confluence API Token:
- Go to Atlassian API Tokens
- Click Create API token
- Give it a name like "AI Assistant"
- Copy the generated token immediately (you won't see it again!)
2. Try It Instantly
# Set your credentials export ATLASSIAN_SITE_NAME="your-company" # for your-company.atlassian.net export ATLASSIAN_USER_EMAIL="[email protected]" export ATLASSIAN_API_TOKEN="your_api_token" # Li
851d0d4a9698OBSERVED · 2026-10-07Exposed tools (5)
1 read · 3 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
conf_delete | destructive | |
conf_get | read | |
conf_patch | write | |
conf_post | write | |
conf_put | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
conf_delete
.releaserc.json
@modelcontextprotocol/sdk, @toon-format/toon, commander, cors, dotenv, express, jmespath, turndown
cat > .env << EOF
Gates applied: no_behavioural_pass, no_license.
851d0d4a9698full audit observations/trust-audit/mcp-server/aashari__atlassian-confluence.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 851d0d4a9698 | SAFE | B | 89 | first audit |
Questions
What is the Atlassian Confluence MCP server?
Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.
What tools does Atlassian Confluence expose?
5 in total: 1 read-only, 3 that write, and 1 that can delete or overwrite (conf_delete). Every one is listed on this page with its risk.
Is Atlassian Confluence safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Atlassian Confluence need?
It reads ATLASSIAN_API_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Atlassian Confluence run?
It speaks stdio and streamable-http, so it runs as a local process your client starts.
How current is this page?
The grade is for one exact copy of the source (851d0d4a9698), read on 2026-10-07. The repository is watched and re-audited when it changes.