confluence_search

THE RISK

Low Risk

Why confluence_search needs a policy

confluence_search performs a read-only query operation that retrieves and returns matching content without creating, modifying, or deleting any data. It has no side effects beyond returning search results. The blast radius of misuse is minimal—an agent could retrieve sensitive information it shouldn't access, but cannot modify or destroy data.

From the tool's definition Tool description: 'Search Confluence content using CQL (Confluence Query Language). Returns matching pages, blog posts, and other content.' The verb 'search' and 'returns' indicate data retrieval with no modification or deletion.

Documented attack patterns abuse exactly the kind of access confluence_search gives an agent:

POLICY

How to control confluence_search

PolicyLayer is an MCP gateway — it sits between your AI agents and Atlassian, and nothing reaches the server without passing your rules. This is the rule we recommend for confluence_search:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "confluence_search": {}
  }
}

confluence_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Atlassian — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Atlassian tools

Destructive confluence_delete_page Delete a page. By default, moves to trash. Use purge option for permanent deletion. Destructive jira_delete_board Delete a board. Warning: This is permanent and cannot be undone. All board configuration w Destructive jira_delete_issue Delete a Jira issue. This action cannot be undone unless the issue is in the trash. Destructive jira_delete_sprint Delete a sprint. Note: Can only delete sprints that have not been started (future state). Destructive jira_remove_issue_link Remove/delete a link between two issues. Requires the link ID. Write jira_link_to_epic Link multiple issues to an epic. Creates Epic-Story links between issues and epic. Write jira_rank_backlog_issues Rank/reorder issues in the backlog. Used to adjust issue priority order before sprint plan Write confluence_add_comment Add a footer comment to a page. Can be a top-level comment or a reply to another comment.

All 51 Atlassian tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about confluence_search

What does the confluence_search tool do? +

Search Confluence content using CQL (Confluence Query Language). Returns matching pages, blog posts, and other content. It is categorised as a Read tool in the Atlassian MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on confluence_search? +

Register the Atlassian MCP server in PolicyLayer and add a rule for confluence_search: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Atlassian. Nothing to install.

What risk level is confluence_search? +

confluence_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit confluence_search? +

Yes. Add a rate_limit block to the confluence_search rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block confluence_search completely? +

Set action: deny in the PolicyLayer policy for confluence_search. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides confluence_search? +

confluence_search is provided by the Atlassian MCP server (xuanxt/atlassian-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Atlassian tool call.

Start from Atlassian, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →