// SCAN REPORT

Atlassian Multi

34 tools. 13 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 2 Jul 2026

13 can modify or destroy data

21 read-only

34 tools total

Community server · catalogue entry verified 02/07/2026

How to control Atlassian Multi ↓

TOOL MAP

What Atlassian Multi exposes to your agents

Read (21) Write / Execute (12) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Atlassian Multi tools

Destructive · High remove_atlassian_account This tool removes (deletes) a configured account, which cannot be undone—a hallmark of Destructive category. Write · Medium add_atlassian_account Adding a new account is a reversible Write operation that creates and persists new configuration state. Write · Medium addCommentToJiraIssue This tool creates new content (a comment) in a Jira issue, which is a write operation. Write · Medium addWorklogToJiraIssue This tool creates or modifies worklog records (time tracking entries) on Jira issues.

13 of Atlassian Multi's 34 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Atlassian Multi

PolicyLayer is an MCP gateway — it sits between your AI agents and Atlassian Multi, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "remove_atlassian_account": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_atlassian_account": {
    "limits": [
      {
        "counter": "add_atlassian_account_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "atlassianUserInfo": {
    "limits": [
      {
        "counter": "atlassianuserinfo_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Atlassian Multi — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ATLASSIAN MULTI →

Instant setup, no code required.

FULL CATALOGUE

All 34 Atlassian Multi tools

DESTRUCTIVE 1 tools

Destructive remove_atlassian_account Remove a configured Atlassian account

WRITE 12 tools

Write add_atlassian_account Add a new Atlassian account (Jira/Confluence workspace) Write addCommentToJiraIssue Add a comment to a Jira issue Write addWorklogToJiraIssue Log time spent on a Jira issue Write createConfluenceFooterComment Add a footer comment to a Confluence page Write createConfluenceInlineComment Add an inline comment to a Confluence page Write createConfluencePage Create a new Confluence page Write createIssueLink Create a link between two Jira issues Write createJiraIssue Create a new Jira issue Write editJiraIssue Update fields on an existing Jira issue Write set_default_atlassian_account Set the default Atlassian account used when no site hint is given Write transitionJiraIssue Transition a Jira issue to a new workflow status Write updateConfluencePage Update an existing Confluence page

READ 21 tools

Read atlassianUserInfo Get current user info for a configured account Read getAccessibleAtlassianResources List all configured Atlassian accounts/sites Read getConfluenceCommentChildren Get replies to a Confluence comment Read getConfluencePage Get a Confluence page by ID Read getConfluencePageDescendants Get child pages of a Confluence page Read getConfluencePageFooterComments Get footer comments on a Confluence page Read getConfluencePageInlineComments Get inline comments on a Confluence page Read getConfluenceSpaces List Confluence spaces Read getIssueLinkTypes Get available issue link types (e.g. Read getJiraIssue Get a Jira issue by key or URL Read getJiraIssueRemoteIssueLinks Get remote issue links (external links) on a Jira issue Read getJiraIssueTypeMetaWithFields Get fields available for a specific issue type in a project Read getJiraProjectIssueTypesMetadata Get issue types and metadata for a Jira project Read getPagesInConfluenceSpace Get pages in a Confluence space Read getTransitionsForJiraIssue Get available workflow transitions for a Jira issue Read getVisibleJiraProjects List Jira projects accessible to the account Read list_atlassian_accounts List all configured Atlassian accounts Read lookupJiraAccountId Search for Jira user accounts by name or email Read searchConfluenceUsingCql Search Confluence using CQL (Confluence Query Language) Read searchJiraIssuesUsingJql Search Jira issues using JQL query Read test_atlassian_connection Test connection and credentials for a configured Atlassian account

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Atlassian Multi

Can an AI agent delete data through the Atlassian Multi MCP server? +

Yes. The Atlassian Multi server exposes 1 destructive tools including remove_atlassian_account. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Atlassian Multi? +

The Atlassian Multi server has 12 write tools including add_atlassian_account, addCommentToJiraIssue, addWorklogToJiraIssue. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Atlassian Multi.

How many tools does the Atlassian Multi MCP server expose? +

34 tools across 3 categories: Destructive, Read, Write. 21 are read-only. 13 can modify, create, or delete data.

How do I enforce a policy on Atlassian Multi? +

Register the Atlassian Multi MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Atlassian Multi tool call.

Deterministic rules across all 34 Atlassian Multi tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ATLASSIAN MULTI →

Instant setup, no code required.

34 Atlassian Multi tools catalogued and risk-classified — across an index of 43,000+ MCP servers.