Confluence CommunicationSAFE
Jira,Wiki MCP
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Overview
This server implements the Model Context Protocol (MCP) for Confluence integration. This version addresses and fixes bugs found in the existing Confluence server, providing a more stable and reliable experience. It provides functionalities to execute CQL queries and retrieve page content from Confluence.
This server follows the MCP client-server architecture:
- Acts as an MCP server providing Confluence functionalities
- Connects to Confluence as a data source
- Communicates with MCP clients through a standardized protocol
How to use
[](https://smithery.ai/server/@zereight/confluence-mcp)
Using with Claude App, Cline, Roo Code
When using with the Claude App, you need to set up your API key and URLs directly.
{
"mcpServers": {
"Confluence communication server": {
"command": "npx",
"args": ["-y", "@zereight/mcp-confluence"],
"env": {
"CONFLUENCE_URL": "https://XXXXXXXX.atlassian.net",
"JIRA_URL": "https://XXXXXXXX.atlassian.net",
"CONFLUENCE_API_MAIL": "Your email",
"CONFLUENCE_API_KEY": "KEY_FROM: https://id.atlassian.com/manage-profile/security/api-tokens",
"CONFLUENCE_IS_CLOUD": "true" // Set to "false" for Server/Data Center
}
}
}
}Using with Cursor
Installing via Smithery
To install Confluence communication server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @zereight/confluence-mcp --client claude
When using with Cursor, you can set up environment variables and run the server as follows:
env [email protected] CONFLUENCE_API_KEY=your-ke
72cd3ffade8eOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-confluence --env CONFLUENCE_API_KEY=${CONFLUENCE_API_KEY} -- npx -y @zereight/[email protected]{
"mcpServers": {
"mcp-confluence": {
"command": "npx",
"args": [
"-y",
"@zereight/[email protected]"
],
"env": {
"CONFLUENCE_API_KEY": "${CONFLUENCE_API_KEY}"
}
}
}
}Exposed tools (13)
7 read · 6 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
create_jira_issue | write | Create a new Jira issue |
create_page | write | Create a new Confluence page |
execute_cql_search | write | Execute a CQL query on Confluence to search pages |
execute_jql_search | write | Execute a JQL query on Jira to search issues |
get_board_sprints | read | Get all sprints from a Jira board |
get_current_sprint | read | Get current active sprint from a board with its issues |
get_epic_issues | read | Get all issues belonging to an epic |
get_page_content | read | Get the content of a Confluence page |
get_sprint_issues | read | Get all issues from a sprint |
get_user_issues | read | Get all issues assigned to or reported by a specific user in a board |
transition_jira_issue | read | Change the status of a Jira issue |
update_jira_issue | write | Update an existing Jira issue |
update_page | write | Update an existing Confluence page |
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 | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
axios, mcp-framework, okhttp, @types/node, typescript
Gates applied: no_behavioural_pass, no_license.
72cd3ffade8efull audit observations/trust-audit/mcp-server/zereight__confluence-communication-1.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 |
|---|---|---|---|---|---|
| 2026-10-08 | 72cd3ffade8e | SAFE | B | 89 | first audit |
Questions
What is the Confluence Communication MCP server?
Jira,Wiki MCP
What tools does Confluence Communication expose?
13 in total: 7 read-only, 6 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Confluence Communication 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.
What credentials does Confluence Communication need?
It reads CONFLUENCE_API_KEY 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 Confluence Communication run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @zereight/mcp-confluence at 1.0.8.
How current is this page?
The grade is for one exact copy of the source (72cd3ffade8e), read on 2026-10-08. The repository is watched and re-audited when it changes.