Search Confluence using CQL.
AI agents call confluence_search to retrieve information from Work Integrations MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation against Confluence documentation. It queries and retrieves data using CQL but does not create, modify, delete, or execute any changes. The action is non-destructive and has no side effects beyond returning search results. Blast radius is minimal—even if an AI agent misuses this tool, it can only access information already readable to the authenticated user.
From the tool's definition Tool name is 'confluence_search' and description states 'Search Confluence using CQL'. CQL (Confluence Query Language) is a search/query mechanism that retrieves information without modifying data.
Attacks that exploit this kind of access
Search Confluence using CQL. It is categorised as a Read tool in the Work Integrations MCP MCP Server, which means it retrieves data without modifying state.
Register the Work Integrations 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 Work Integrations MCP. Nothing to install.
confluence_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.
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.
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.
confluence_search is provided by the Work Integrations MCP server (nazarky/workspace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →