Search Confluence content using CQL (Confluence Query Language). Example: type=page AND space.key=DEV AND text~
AI agents call confluence_search_content to retrieve information from Sage MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a classic Read operation—it queries and retrieves Confluence data. The medium severity reflects that search functionality could expose sensitive documentation, internal planning documents, or credentials if an agent performs broad searches without proper filtering, but the action itself is non-destructive. Confidence is high because the intent is explicitly stated as search/query functionality.
From the tool's definition Tool performs search operations on Confluence content using CQL, which retrieves or queries data without modifying it. The description explicitly states 'Search Confluence content' with no mention of creating, updating, or deleting data.
Documented attack patterns abuse exactly the kind of access confluence_search_content gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sage MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for confluence_search_content:
{
"version": "1",
"default": "deny",
"tools": {
"confluence_search_content": {}
}
}confluence_search_content is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search Confluence content using CQL (Confluence Query Language). Example: type=page AND space.key=DEV AND text~. It is categorised as a Read tool in the Sage MCP MCP Server, which means it retrieves data without modifying state.
Register the Sage MCP server in PolicyLayer and add a rule for confluence_search_content: 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 Sage MCP. Nothing to install.
confluence_search_content 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_content 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_content. 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_content is provided by the Sage MCP server (sagemcp/sagemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 359 Sage MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
359 Sage MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.