confluence_search_cql
AI agents call confluence_search_cql to retrieve information from Inhouse Confluence without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
CQL search operations retrieve and filter Confluence content without modifying data. However, severity is medium rather than low because CQL queries on a Confluence instance could expose sensitive internal documentation, access control information, or metadata about enterprise content architecture depending on what the user searches for and the instance's permission model.
From the tool's definition Tool name contains 'search' and 'cql' (Confluence Query Language), indicating query-based data retrieval. Server description explicitly lists 'search' as a core capability alongside 'content retrieval.' The empty tool description prevents full assessment but…
Attacks that exploit this kind of access
confluence_search_cql. It is categorised as a Read tool in the Inhouse Confluence MCP Server, which means it retrieves data without modifying state.
Register the Inhouse Confluence MCP server in PolicyLayer and add a rule for confluence_search_cql: 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 Inhouse Confluence. Nothing to install.
confluence_search_cql 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_cql 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_cql. 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_cql is provided by the Inhouse Confluence MCP server (janus-06/inhouse_confluence_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 →